A collective AI via lifelong learning and sharing at the edge
Open accessThe DOI matches its Crossref record; 184 of the 184 references it cites were found in a registry or an index.
Abstract
One vision of a future artificial intelligence (AI) is where many separate units can learn independently over a lifetime and share their knowledge with each other. The synergy between lifelong learning and sharing has the potential to create a society of AI systems, as each individual unit can contribute to and benefit from the collective knowledge. Essential to this vision are the abilities to learn multiple skills incrementally during a lifetime, to exchange knowledge among units via a common language, to use both local data and communication to learn, and to rely on edge devices to host the necessary decentralized computation and data. The result is a network of agents that can quickly respond to and learn new tasks, that collectively hold more knowledge than a single agent and that can extend current knowledge in more diverse ways than a single agent. Open research questions include when and what knowledge should be shared to maximize both the rate of learning and the long-term learning performance. Here we review recent machine learning advances converging towards creating a collective machine-learned intelligence. We propose that the convergence of such scientific and technological advances will lead to the emergence of new types of scalable, resilient and sustainable AI systems. An emerging research area in AI is developing multi-agent capabilities with collections of interacting AI systems. Andrea Soltoggio and colleagues develop a vision for combining such approaches with current edge computing technology and lifelong learning advances. The envisioned network of AI agents could quickly learn new tasks in open-ended applications, with individual AI agents independently learning and contributing to and benefiting from collective knowledge.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Despite the aforementioned challenges, ShELL algorithms have the potential to augment the capabilities of the latest and most advanced AI models, including transformer networks 196,197 and foundation models 198,199 .”
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · cited 2×
“Category 1 is typical of edge-AI devices that incorporate trained models for inference, for example, smartphones, smart cameras and autonomous vehicles 17,113,114 .”
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899
Advances and Open Problems in Federated Learning
Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.04977 · Cited by 7,857
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Intelligent agents: theory and practice
Wooldridge, M., & Jennings, N. R. (1995) · The Knowledge Engineering Review · doi:10.1017/s0269888900008122 · Cited by 6,810
A Comprehensive Survey on Transfer Learning
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3004555 · Cited by 6,678 · cited 1×
“Reusing previously acquired knowledge when learning a new task is key to transfer learning 62–64 .”
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 1×
“The same assumption that task similarities can be exploited motivates multi-task learning 71–74 .”
International Conference on Learning Representations (ICLR 2013)
松尾, 豊. (2013) · 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence · Cited by 6,286
A Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607 · cited 1×
“Category 1 is typical of edge-AI devices that incorporate trained models for inference, for example, smartphones, smart cameras and autonomous vehicles 17,113,114 .”
Machine learning: Algorithms, real-world applications and research directions
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00592-x · Cited by 5,583 · cited 1×
“Despite the challenges described above, real-world applications of ML demand increasingly more adaptive systems that can continuously improve during deployment, face a large variety of new and diverse tasks 48 , and mimic lifelong learning properties of biological systems 11,49 .”
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“The concept that specific previous knowledge is beneficial to learning new tasks is also exploited in curriculum learning 78,79 , where the particular sequence and complexity of the tasks are designed to facilitate learning.”
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537 · cited 2×
“…gate arrays, application-specific integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 ,…”
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015 · cited 1×
“The application of ML to medical domains has recently benefited from distributed approaches based on federated learning 185 , in particular through enabling multi-institution collaborations 186 .”
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595 · cited 1×
“Despite the aforementioned challenges, ShELL algorithms have the potential to augment the capabilities of the latest and most advanced AI models, including transformer networks 196,197 and foundation models 198,199 .”
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2101.01169 · Cited by 3,594 · cited 1×
“Despite the aforementioned challenges, ShELL algorithms have the potential to augment the capabilities of the latest and most advanced AI models, including transformer networks 196,197 and foundation models 198,199 .”
The Future of Digital Health with Federated Learning
Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B., Maier-Hein, K., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.08119 · Cited by 3,495 · cited 1×
“The application of ML to medical domains has recently benefited from distributed approaches based on federated learning 185 , in particular through enabling multi-institution collaborations 186 .”
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
Park, J. J., Florence, P., Straub, J., Newcombe, R., & Lovegrove, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00025 · Cited by 3,422 · cited 1×
“With the recent advances in implicit neural representations (INRs) 173 , the neural radiance fields (NeRFs) 174,175 and signed distance functions (SDFs) 176,177 , there is an emerging interest in using such INRs in MAAS.”
A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection
Buczak, A. L., & Guven, E. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2015.2494502 · Cited by 3,332
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096 · cited 1×
“Examples of model components in LLMs are low-rank adaptation 99 , novel model reparametrization techniques 66,100 and soft prompts 101 that allow for fine-tuning of large models by only adjusting a significantly smaller set of parameters in specific parts of the model 65 .”
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092 · cited 1×
“Examples of model components in LLMs are low-rank adaptation 99 , novel model reparametrization techniques 66,100 and soft prompts 101 that allow for fine-tuning of large models by only adjusting a significantly smaller set of parameters in specific parts of the model 65 .”
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · cited 1×
“Despite the aforementioned challenges, ShELL algorithms have the potential to augment the capabilities of the latest and most advanced AI models, including transformer networks 196,197 and foundation models 198,199 .”
Self-citationCatastrophic forgetting in connectionist networks
French, R. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01294-2 · Cited by 2,311
Memory devices and applications for in-memory computing
Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R., & Eleftheriou, E. (2020) · Nature Nanotechnology · doi:10.1038/s41565-020-0655-z · Cited by 2,289 · cited 1×
“…integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 , integrated photonic tensor core 137–139 and others 128 .”
An Overview of Multi-Task Learning in Deep Neural Networks
Ruder, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05098 · Cited by 2,265
Deep visual domain adaptation: A survey
Wang, M., & Deng, W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.083 · Cited by 2,209
Towards spike-based machine intelligence with neuromorphic computing
Roy, K., Jaiswal, A., & Panda, P. (2019) · Nature · doi:10.1038/s41586-019-1677-2 · Cited by 2,190
Self-citationFoundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · cited 1×
“If such knowledge is available in medical datasets, ShELL technology could be the key to delivering personalized, task-specific knowledge to the point of care 187 .”
Superintelligence: paths, dangers, strategies
(2015) · Choice Reviews Online · doi:10.5860/choice.187536 · Cited by 1,979
Parallel convolutional processing using an integrated photonic tensor core
Feldmann, J., Youngblood, N., Karpov, M., Gehring, H., Li, X., Stappers, M., Le Gallo, M., Fu, X., Lukashchuk, A., Raja, A. S., et al. (2021) · Nature · doi:10.1038/s41586-020-03070-1 · Cited by 1,900 · cited 1×
“…integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 , integrated photonic tensor core 137–139 and others 128 .”
Machine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842 · cited 1×
“In addition to established ML metrics 91 and recently developed LL metrics 36,37,45–47, 92 , ShELL-specific ShELL-specific Considering a single LL agent as a baseline, two metrics can be defined to measure objective 1: (1) how much performance gains can n agents achieve within a determined time…”
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Photonics for artificial intelligence and neuromorphic computing
Shastri, B. J., Tait, A. N., Ferreira de Lima, T., Pernice, W. H. P., Bhaskaran, H., Wright, C. D., & Prucnal, P. R. (2021) · Nature Photonics · doi:10.1038/s41566-020-00754-y · Cited by 1,756 · cited 1×
“…integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 , integrated photonic tensor core 137–139 and others 128 .”
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649
A Continual Learning Survey: Defying Forgetting in Classification Tasks
Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3057446 · Cited by 1,647 · cited 2×
“The computational load of LL approaches is affected by the specific type of algorithm, for example, replay 126 , regularization or parameter isolation methods 32,44 , which could involve different use of CPU, GPU or memory 127 .”
A continual learning survey: Defying forgetting in classification tasks
De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2019) · arXiv · doi:10.48550/arxiv.1909.08383 · Cited by 1,647
Sheller, M. J., Edwards, B., Reina, G. A., Martin, J., Pati, S., Kotrotsou, A., Milchenko, M., Xu, W., Marcus, D., Colen, R. R., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-69250-1 · Cited by 1,646 · cited 1×
“The application of ML to medical domains has recently benefited from distributed approaches based on federated learning 185 , in particular through enabling multi-institution collaborations 186 .”
pixelNeRF: Neural Radiance Fields from One or Few Images
Yu, A., Ye, V., Tancik, M., & Kanazawa, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00455 · Cited by 1,560 · cited 1×
“With the recent advances in implicit neural representations (INRs) 173 , the neural radiance fields (NeRFs) 174,175 and signed distance functions (SDFs) 176,177 , there is an emerging interest in using such INRs in MAAS.”
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503 · cited 1×
“The main aims when performing training on edge devices 52,53 are to reduce data transfer and maintain privacy.”
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J.-F., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2019) · Nature · doi:10.1038/s41586-019-1138-y · Cited by 1,364
Multiagent systems: A survey from a machine learning perspective
Stone, P., & Veloso, M. (2000) · Autonomous Robots · doi:10.1023/a:1008942012299 · Cited by 1,218 · cited 1×
“Multi-agent and distributed AI systems have been studied for decades 3–5 , albeit often with a focus on cooperation to solve a single task 6 or competition in game theory studies 7 .”
Self-citationThe Complexity of Decentralized Control of Markov Decision Processes
Bernstein, D. S., Givan, R., Immerman, N., & Zilberstein, S. (2002) · Mathematics of Operations Research · doi:10.1287/moor.27.4.819.297 · Cited by 1,192
Parameter-efficient fine-tuning of large-scale pre-trained language models
Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C.-M., Chen, W., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00626-4 · Cited by 1,191 · cited 2×
“This approach has obvious benefits in real-world applications of ML, including recently developed methods for large language models (LLMs) namely parameter efficient fine-tuning 65,66 .”
Multi-Task Deep Neural Networks for Natural Language Understanding
Liu, X., He, P., Chen, W., & Gao, J. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1441 · Cited by 1,154 · cited 1×
“The same assumption that task similarities can be exploited motivates multi-task learning 71–74 .”
Self-citationEdge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., & Zomaya, A. Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2984887 · Cited by 1,147
Taskonomy: Disentangling Task Transfer Learning
Zamir, A. R., Sax, A., Shen, W., Guibas, L., Malik, J., & Savarese, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00391 · Cited by 1,128
Federated learning on non-IID data: A survey
Zhu, H., Xu, J., Liu, S., & Jin, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.098 · Cited by 1,062
Dorri, A., Kanhere, S. S., & Jurdak, R. (2018) · IEEE Access · doi:10.1109/access.2018.2831228 · Cited by 1,043
A survey of unsupervised deep domain adaptation
Wilson, G., & Cook, D. J. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3400066 · Cited by 987
Natural pedagogy as evolutionary adaptation
Csibra, G., & Gergely, G. (2011) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2010.0319 · Cited by 970
Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
Li, E., Zeng, L., Zhou, Z., & Chen, X. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2946140 · Cited by 929 · cited 1×
“The successful deployment of neural models on edge devices has led manufacturers to incorporate deep learning accelerators for inference on most portable devices 59,115 and to the optimization of deep learning algorithms 116 .”
Neuro-inspired computing chips
Zhang, W., Gao, B., Tang, J., Yao, P., Yu, S., Chang, M.-F., Yoo, H.-J., Qian, H., & Wu, H. (2020) · Nature Electronics · doi:10.1038/s41928-020-0435-7 · Cited by 892 · cited 1×
“…integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 , integrated photonic tensor core 137–139 and others 128 .”
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. (2021) · Deakin Research Online (Deakin University) · Cited by 889
Meta-Learning in Neural Networks: A Survey
Hospedales, T. M., Antoniou, A., Micaelli, P., & Storkey, A. J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3079209 · Cited by 886
Generalized Out-of-Distribution Detection: A Survey
Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02117-4 · Cited by 884 · cited 2×
“Novelty detection 87,89,95 and context information 96,97 are particularly relevant for applications with many, possibly interfering, tasks.”
A Survey on Distributed Machine Learning
Verbraeken, J., Wolting, M., Katzy, J., Kloppenburg, J., Verbelen, T., & Rellermeyer, J. S. (2021) · ACM Computing Surveys · doi:10.1145/3377454 · Cited by 872 · cited 1×
“Many agents, by sharing knowledge, can sum their efforts to achieve collectively faster and more complete learning on a large amount of data, as is being show-cased by federated learning approaches 22,23 and distributed ML 24 .”
Governing artificial intelligence: ethical, legal and technical opportunities and challenges
Cath, C. (2018) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2018.0080 · Cited by 745
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification
Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van de Weijer, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3213473 · Cited by 740 · cited 1×
“In addition to established ML metrics 91 and recently developed LL metrics 36,37,45–47, 92 , ShELL-specific ShELL-specific Considering a single LL agent as a baseline, two metrics can be defined to measure objective 1: (1) how much performance gains can n agents achieve within a determined time…”
Self-citationThree types of incremental learning
van de Ven, G. M., Tuytelaars, T., & Tolias, A. S. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00568-3 · Cited by 665
Embedded Devices for Neuromorphic Time-Series Assessment
Mazumder, A. N., Hosseini, M., & Mohsenin, T. (2022) · Research Explorer (The University of Manchester) · doi:10.13016/m2ksy0-wxr3 · Cited by 652
Towards Making Systems Forget with Machine Unlearning
Cao, Y., & Yang, J. (2015) · 2015 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2015.35 · Cited by 622 · cited 1×
“In addition, the processes used by LL agents when integrating new knowledge in their models may be difficult to reverse, that is, to unlearn 203 .”
A Brief Review of Domain Adaptation
Farahani, A., Voghoei, S., Rasheed, K., & Arabnia, H. R. (2021) · Transactions on Computational Science and Computational Intelligence · doi:10.1007/978-3-030-71704-9_65 · Cited by 615
The growing energy footprint of artificial intelligence
de Vries, A. (2023) · Joule · doi:10.1016/j.joule.2023.09.004 · Cited by 597 · cited 2×
“Knowledge reuse could lead to long-term scalability of AI that may be fully achieved only if machine-learned knowledge can be added incrementally and shared among agents, resulting also in the reduction of energy and carbon footprint of increasingly large systems 25,26,200,207 .”
A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Chen, X., & Wang, X. (2022) · ACM Computing Surveys · doi:10.1145/3447582 · Cited by 590 · cited 1×
“A similar meta-learning process occurs with neural architecture search (NAS) 105,106 .”
Singh, R., & Gill, S. S. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.02.004 · Cited by 572 · cited 1×
“As a result, the efficiency of learning algorithms, power requirements and compute/memory constraints play a more Perspective https://doi.org/10.1038/s42256-024-00800-2 important role than in ML on large servers 109–112 .”
InfluentialA Survey of Deep Learning Methods for Cyber Security
Berman, D. S., Buczak, A. L., Chavis, J. S., & Corbett, C. L. (2019) · Information · doi:10.3390/info10040122 · Cited by 569 · cited 1×
“ML applications to cyber security have grown in recent years with scientific efforts and integration into commercial products 189–191 .”
A Survey on Machine Learning Techniques for Cyber Security in the Last Decade
Shaukat, K., Luo, S., Varadharajan, V., Hameed, I. A., & Xu, M. (2020) · IEEE Access · doi:10.1109/access.2020.3041951 · Cited by 530
A Survey of Zero-Shot Learning: Settings, Methods, and Applications
Wang, W., Zheng, V. W., Yu, H., & Miao, C. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3293318 · Cited by 528
Edge Machine Learning for AI-Enabled IoT Devices: A Review
Merenda, M., Porcaro, C., & Iero, D. (2020) · Sensors · doi:10.3390/s20092533 · Cited by 523 · cited 2×
“However, one aspect that makes ShELL possible is for each agent to rely on its own computation to learn in the proximity of sensors and actuators 42,43,107,108 .”
Deep Learning with Low Precision by Half-Wave Gaussian Quantization
Cai, Z., He, X., Sun, J., & Vasconcelos, N. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.574 · Cited by 498
NeRF++: Analyzing and Improving Neural Radiance Fields
Zhang, K., Riegler, G., Snavely, N., & Koltun, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.07492 · Cited by 487 · cited 1×
“With the recent advances in implicit neural representations (INRs) 173 , the neural radiance fields (NeRFs) 174,175 and signed distance functions (SDFs) 176,177 , there is an emerging interest in using such INRs in MAAS.”
Embracing Change: Continual Learning in Deep Neural Networks
Hadsell, R., Rao, D., Rusu, A. A., & Pascanu, R. (2020) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2020.09.004 · Cited by 467
Thrun, S. (1998) · Learning to Learn · doi:10.1007/978-1-4615-5529-2_8 · Cited by 413
Sustainable AI: Environmental Implications, Challenges and Opportunities
Wu, C.-J., Raghavendra, R., Gupta, U., Acun, B., Ardalani, N., Maeng, K., Chang, G., Behram, F. A., Huang, J., Bai, C., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.00364 · Cited by 405
Machine Learning at the Network Edge: A Survey
Murshed, M. G. S., Murphy, C., Hou, D., Khan, N., Ananthanarayanan, G., & Hussain, F. (2022) · ACM Computing Surveys · doi:10.1145/3469029 · Cited by 402 · cited 1×
“As a result, the efficiency of learning algorithms, power requirements and compute/memory constraints play a more Perspective https://doi.org/10.1038/s42256-024-00800-2 important role than in ML on large servers 109–112 .”
InfluentialTowards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
Henderson, P., Hu, J., Romoff, J., Brunskill, E., Jurafsky, D., & Pineau, J. (2020) · arXiv · doi:10.48550/arxiv.2002.05651 · Cited by 393 · cited 2×
“Knowledge reuse could lead to long-term scalability of AI that may be fully achieved only if machine-learned knowledge can be added incrementally and shared among agents, resulting also in the reduction of energy and carbon footprint of increasingly large systems 25,26,200,207 .”
Decentralized Federated Averaging
Sun, T., Li, D., & Wang, B. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3196503 · Cited by 388 · cited 1×
“Most federated learning approaches, although distributed, update a single central model, however decentralized approaches have been reported 61 .”
Yang, J., Shen, X., Xing, J., Tian, X., Li, H., Deng, B., Huang, J., & Hua, X.-S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00748 · Cited by 387 · cited 1×
“The requirement for deployment on small devices has lead to studies that measure and optimize computational loads of LL algorithms 18,44,47,119–121 , and more generally for model training with an emphasis on efficiency, for example, via quantization 122–125 .”
FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction
Gao, L., Fu, H., Li, L., Chen, Y., Xu, M., & Xu, C.-Z. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00987 · Cited by 374 · cited 1×
“Recently, federated learning studies have started to consider LL-related issues, such as non-IID data across locations and time 54–56 , thus identifying the need to prevent catastrophic forgetting 57,58 .”
Artificial intelligence, cyber-threats and industry 4.0: challenges and opportunities
Bécue, A., Praça, I., & Gama, J. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09942-2 · Cited by 368 · cited 1×
“Concerns over the impact of cyber attacks and cyber warfare continuously increase as more and more aspects of our lives depend on connected devices 188 .”
Learning task-state representations
Niv, Y. (2019) · Nature Neuroscience · doi:10.1038/s41593-019-0470-8 · Cited by 356 · cited 1×
“Novelty detection 87,89,95 and context information 96,97 are particularly relevant for applications with many, possibly interfering, tasks.”
From distributed machine learning to federated learning: a survey
Liu, J., Huang, J., Zhou, Y., Li, X., Ji, S., Xiong, H., & Dou, D. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01664-x · Cited by 356 · cited 2×
“The ability to perform ML on a large number of distributed edge devices has been extensively investigated in the field of federated learning 15,23,50,51 .”
Managing extreme AI risks amid rapid progress
Bengio, Y., Hinton, G., Yao, A., Song, D., Abbeel, P., Darrell, T., Harari, Y. N., Zhang, Y.-Q., Xue, L., Shalev-Shwartz, S., et al. (2024) · Science · doi:10.1126/science.adn0117 · Cited by 349
Selective Experience Replay for Lifelong Learning
Isele, D., & Cosgun, A. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11595 · Cited by 347
Federated Learning in Edge Computing: A Systematic Survey
Abreha, H. G., Hayajneh, M., & Serhani, M. A. (2022) · Sensors · doi:10.3390/s22020450 · Cited by 342 · cited 1×
“The main aims when performing training on edge devices 52,53 are to reduce data transfer and maintain privacy.”
Generalized Out-of-Distribution Detection: A SurveyPreprint
Yang, J., Zhou, K., Li, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.11334 · Cited by 310 · cited 2×
“Novelty detection 87,89,95 and context information 96,97 are particularly relevant for applications with many, possibly interfering, tasks.”
Review on space robotics: Toward top-level science through space exploration
Gao, Y., & Chien, S. (2017) · Science Robotics · doi:10.1126/scirobotics.aan5074 · Cited by 296 · cited 1×
“…(1) large delays and limited bandwidth between distant locations 180 ; (2) the requirement for autonomous navigation systems and spacecraft control 181 , ML-aided sensing 182,183 and autonomous decision-making; (3) the need for self-adaptation due to faults, unforeseen or changing conditions; (4)…”
Learn from Others and Be Yourself in Heterogeneous Federated Learning
Huang, W., Ye, M., & Du, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00990 · Cited by 280 · cited 1×
“In particular, in domains where personalization and geographical variations are important, the addition of LL, multi-task or meta-learning algorithms to federated learning has become a priority 59,60 .”
A Survey of On-Device Machine Learning: An Algorithms and Learning Theory Perspective
Dhar, S., Guo, J., Liu, J., Tripathi, S., Kurup, U., & Shah, M. (2021) · ACM Transactions on Internet of Things · doi:10.1145/3450494 · Cited by 276
Exploring Neuromorphic Computing Based on Spiking Neural Networks: Algorithms to Hardware
Rathi, N., Chakraborty, I., Kosta, A., Sengupta, A., Ankit, A., Panda, P., & Roy, K. (2023) · ACM Computing Surveys · doi:10.1145/3571155 · Cited by 267 · cited 1×
“…integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing 130 , neuromorphic computing 131–135 , spiking neural networks 135,136 , integrated photonic tensor core 137–139 and others 128 .”
Self-citationDon't forget, there is more than forgetting: new metrics for Continual LearningPreprint
Díaz-Rodríguez, N., Lomonaco, V., Filliat, D., & Maltoni, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.13166 · Cited by 255 · cited 2×
“In addition to established ML metrics 91 and recently developed LL metrics 36,37,45–47, 92 , ShELL-specific ShELL-specific Considering a single LL agent as a baseline, two metrics can be defined to measure objective 1: (1) how much performance gains can n agents achieve within a determined time…”
Multi-agent team cooperation: A game theory approach
Semsar-Kazerooni, E., & Khorasani, K. (2009) · Automatica · doi:10.1016/j.automatica.2009.06.006 · Cited by 240 · cited 1×
“Multi-agent and distributed AI systems have been studied for decades 3–5 , albeit often with a focus on cooperation to solve a single task 6 or competition in game theory studies 7 .”
Dataset Distillation by Matching Training Trajectories
Cazenavette, G., Wang, T., Torralba, A., Efros, A. A., & Zhu, J.-Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01045 · Cited by 240 · cited 1×
“Distillation approaches 157,158 may involve data sharing (Fig.”
Biological underpinnings for lifelong learning machines
Kudithipudi, D., Aguilar-Simon, M., Babb, J., Bazhenov, M., Blackiston, D., Bongard, J., Brna, A. P., Chakravarthi Raja, S., Cheney, N., Clune, J., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00452-0 · Cited by 236 · cited 2×
“This programme investigated both biological inspiring principles 11 and core LL algorithms, improving the understanding of algorithmic properties and metrics for evaluation 36,37 .”
Self-citationDecentralized Control of Cooperative Systems: Categorization and Complexity Analysis
Goldman, C. V., & Zilberstein, S. (2004) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1427 · Cited by 232 · cited 1×
“Managing the connectivity of a potentially large number of agents is essential to achieve scalability 193,194 .”
Towards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2020) · arXiv · doi:10.48550/arxiv.2012.13490 · Cited by 227
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M. E., & Stone, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04960 · Cited by 224 · cited 1×
“The concept that specific previous knowledge is beneficial to learning new tasks is also exploited in curriculum learning 78,79 , where the particular sequence and complexity of the tasks are designed to facilitate learning.”
Self-citationTowards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13673 · Cited by 224
Dealing with non-stationary environments using context detection
da Silva, B. C., Basso, E. W., Bazzan, A. L. C., & Engel, P. M. (2006) · International Conference on Machine Learning · doi:10.1145/1143844.1143872 · Cited by 209 · cited 1×
“Novelty detection 87,89,95 and context information 96,97 are particularly relevant for applications with many, possibly interfering, tasks.”
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
Cai, H., Lin, J., Lin, Y., Liu, Z., Tang, H., Wang, H., Zhu, L., & Han, S. (2022) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3486618 · Cited by 197 · cited 2×
“The requirement for deployment on small devices has lead to studies that measure and optimize computational loads of LL algorithms 18,44,47,119–121 , and more generally for model training with an emphasis on efficiency, for example, via quantization 122–125 .”
Network resilience: a systematic approach
Smith, P., Hutchison, D., Sterbenz, J. P. G., Schöller, M., Fessi, A., Karaliopoulos, M., Lac, C., & Plattner, B. (2011) · IEEE Communications Magazine · doi:10.1109/mcom.2011.5936160 · Cited by 194
Wang, T., Zhu, J.-Y., Torralba, A., & Efros, A. A. (2018) · arXiv · doi:10.48550/arxiv.1811.10959 · Cited by 194
A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Chen, X., & Wang, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02903 · Cited by 193 · cited 1×
“A similar meta-learning process occurs with neural architecture search (NAS) 105,106 .”
Domain Adaptation Without Source Data
Kim, Y., Cho, D., Han, K., Panda, P., & Hong, S. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3110179 · Cited by 190
Self-citationNon-IID data and Continual Learning processes in Federated Learning: A long road ahead
Criado, M. F., Casado, F. E., Iglesias, R., Regueiro, C. V., & Barro, S. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.07.024 · Cited by 186
An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications
Ajani, T. S., Imoize, A. L., & Atayero, A. A. (2021) · Sensors · doi:10.3390/s21134412 · Cited by 176
Distral: Robust Multitask Reinforcement Learning
Teh, Y. W., Bapst, V., Czarnecki, W. M., Quan, J., Kirkpatrick, J., Hadsell, R. T., Heess, N., & Pascanu, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.04175 · Cited by 172 · cited 1×
“Accompanying policies with representative data (that is, core sets, special cases and so on) could lead to a more effective knowledge transfer, particularly for heterogeneous systems 156,161 .”
Neuro-symbolic artificial intelligence: Current trends
Sarker, M. K., Zhou, L., Eberhart, A., & Hitzler, P. (2022) · AI Communications · doi:10.3233/aic-210084 · Cited by 169
Pathways to efficient neuromorphic computing with non-volatile memory technologies
Chakraborty, I., Jaiswal, A., Saha, A. K., Gupta, S. K., & Roy, K. (2020) · Applied Physics Reviews · doi:10.1063/1.5113536 · Cited by 168
Self-citationA Survey of Methods for Low-Power Deep Learning and Computer Vision
Goel, A., Tung, C., Lu, Y.-H., & Thiruvathukal, G. K. (2020) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot48130.2020.9221198 · Cited by 146 · cited 1×
“The requirement for deployment on small devices has lead to studies that measure and optimize computational loads of LL algorithms 18,44,47,119–121 , and more generally for model training with an emphasis on efficiency, for example, via quantization 122–125 .”
Thrun, S., & Mitchell, T. M. (1994) · Defense Technical Information Center (DTIC) · doi:10.21236/ada285342 · Cited by 145
Wortsman, M., Ramanujan, V., Liu, R., Kembhavi, A., Rastegari, M., Yosinski, J., & Farhadi, A. (2020) · arXiv · doi:10.48550/arxiv.2006.14769 · Cited by 144 · cited 1×
“Parameter isolation approaches based on modulating masks 40,146,147 have shown promise to facilitate task-specific transfer of knowledge.”
Mundt, M., Hong, Y., Pliushch, I., & Ramesh, V. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.014 · Cited by 132
A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing
Toczé, K., & Nadjm-Tehrani, S. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/7476201 · Cited by 124
Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks
Soltoggio, A., Stanley, K. O., & Risi, S. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.013 · Cited by 121 · cited 1×
“With the objective to create always-learning algorithms that do not have separate training and deployment phases 34 , can improve over time and can deal with surprise events and unexpected data, the Defense Advanced Research Projects Agency (DARPA) funded the Lifelong Learning Machine programme 35 .”
Self-citationEdge Intelligence: Architectures, Challenges, and Applications
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12172 · Cited by 120
Computationally Budgeted Continual Learning: What Does Matter?
Prabhu, A., Hammoud, H. A. A. K., Dokania, P. K., Torr, P. H. S., Lim, S.-N., Ghanem, B., & Bibi, A. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00360 · Cited by 118 · cited 3×
“The computational load of LL approaches is affected by the specific type of algorithm, for example, replay 126 , regularization or parameter isolation methods 32,44 , which could involve different use of CPU, GPU or memory 127 .”
Review of ASIC accelerators for deep neural network
Machupalli, R., Hossain, M., & Mandal, M. K. (2022) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2022.104441 · Cited by 108 · cited 3×
“…2) motivate research in more powerful accelerators: in addition to GPUs and field-programmable gate arrays, application-specific integrated circuits 128 have been developed for ML tasks, including tensor processing units (TPU) 129 , and emerging computational approaches such as in-memory computing…”
SparCL: Sparse Continual Learning on the Edge
Wang, Z., Zhan, Z., Gong, Y., Yuan, G., Niu, W., Jian, T., Ren, B., Ioannidis, S., Wang, Y., & Dy, J. (2022) · neural information processing systems · doi:10.52202/068431-1481 · Cited by 108
Real-Time Evaluation in Online Continual Learning: A New Hope
Ghunaim, Y., Bibi, A., Alhamoud, K., Alfarra, M., Hammoud, H. A. A. K., Prabhu, A., Torr, P. H. S., & Ghanem, B. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01144 · Cited by 106 · cited 3×
“The requirement for deployment on small devices has lead to studies that measure and optimize computational loads of LL algorithms 18,44,47,119–121 , and more generally for model training with an emphasis on efficiency, for example, via quantization 122–125 .”
AI4MARS: A Dataset for Terrain-Aware Autonomous Driving on Mars
Swan, R. M., Atha, D., Leopold, H. A., Gildner, M., Oij, S., Chiu, C., & Ono, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00226 · Cited by 104 · cited 1×
“…bandwidth between distant locations 180 ; (2) the requirement for autonomous navigation systems and spacecraft control 181 , ML-aided sensing 182,183 and autonomous decision-making; (3) the need for self-adaptation due to faults, unforeseen or changing conditions; (4) the limited power and…”
Usmanova, A., Portet, F., Lalanda, P., & Vega, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04197 · Cited by 100 · cited 2×
“Distillation methods have been used in a continual federated learning approach to diffuse computation across edge devices 156 .”
Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software
Sipola, T., Alatalo, J., Kokkonen, T., & Rantonen, M. (2022) · 2022 31st Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct54823.2022.9770931 · Cited by 100 · cited 1×
“However, one aspect that makes ShELL possible is for each agent to rely on its own computation to learn in the proximity of sensors and actuators 42,43,107,108 .”
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
Riemer, M., Cases, I., Ajemian, R., Liu, M., Rish, I., Tu, Y., & Tesauro, G. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11910 · Cited by 98 · cited 1×
“Meta-learning was also shown to be successful in a decentralized framework 76 and in combination with continual learning 77 .”
Managing AI Risks in an Era of Rapid Progress
Bengio, Y., Hinton, G., Yao, A., Song, D., Abbeel, P., Harari, Y., Zhang, Y.-Q., Xue, L., Shalev-Shwartz, S., Hadfield, G. K., et al. (2023) · arXiv.org · doi:10.48550/arxiv.2310.17688 · Cited by 89 · cited 1×
“Sharing among LL agents that maintain individual objectives and agency provide an efficient, diverse and resilient democracy of AI to contrast the emergence of few, large and centralized AI models 205,206 .”
Asynchronous Federated Continual Learning
Shenaj, D., Toldo, M., Rigon, A., & Zanuttigh, P. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00534 · Cited by 86
Integrated Photonic Tensor Processing Unit for a Matrix Multiply: A Review
Peserico, N., Shastri, B. J., & Sorger, V. J. (2023) · Journal of Lightwave Technology · doi:10.1109/jlt.2023.3269957 · Cited by 84
Zhang, Y., Bai, Y., Wang, M., & Hu, J. S. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2987746 · Cited by 76 · cited 1×
“…this paper, we note that ShELL technology can be beneficial in this domain due to (1) large delays and limited bandwidth between distant locations 180 ; (2) the requirement for autonomous navigation systems and spacecraft control 181 , ML-aided sensing 182,183 and autonomous decision-making; (3)…”
Multi-Robot Active Sensing and Environmental Model Learning With Distributed Gaussian Process
Jang, D., Yoo, J., Son, C. Y., Kim, D., & Kim, H. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3010456 · Cited by 76 · cited 1×
“Multi-agent active sensing (MAAS) refers to the problem of coordinating multiple agents to strategically gather information from an underlying domain of interest to collectively achieve a desired sensing objective, for example, target detection or generative modelling of the domain 170,171 .”
A review on multimodal zero‐shot learning
Cao, W., Wu, Y., Sun, Y., Zhang, H., Ren, J., Gu, D., & Wang, X. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1488 · Cited by 70 · cited 1×
“Finally, reusing knowledge from a domain to solve a new problem is also central in zero-shot learning 80–84 .”
Mehlin, V., Schacht, S., & Lanquillon, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.01980 · Cited by 69 · cited 1×
“The successful deployment of neural models on edge devices has led manufacturers to incorporate deep learning accelerators for inference on most portable devices 59,115 and to the optimization of deep learning algorithms 116 .”
Tsuda, B., Tye, K. M., Siegelmann, H. T., & B, T. J. S. A. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2009591117 · Cited by 64
Self-citationEfficient Feature Transformations for Discriminative and Generative Continual Learning
Verma, V. K., Liang, K. J., Mehta, N., Rai, P., & Carin, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01365 · Cited by 62 · cited 1×
“A similar concept is also exploited in other studies 102,103,148–150 , where task-agnostic backbones are combined with small sets of task-specific parameters that allow for knowledge transfer with minimal changes to a model 151,152 .”
Foundation Models for Decision Making: Problems, Methods, and Opportunities
Yang, S., Nachum, O., Du, Y., Wei, J., Abbeel, P., & Schuurmans, D. (2023) · arXiv · doi:10.48550/arxiv.2303.04129 · Cited by 60 · cited 1×
“Despite the aforementioned challenges, ShELL algorithms have the potential to augment the capabilities of the latest and most advanced AI models, including transformer networks 196,197 and foundation models 198,199 .”
Multi-task Sequence to Sequence Learning
Luong, M.-T., Le, Q. V., Sutskever, I., Vinyals, O., & Kaiser, Ł. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06114 · Cited by 56
Collective Scientific Knowledge
Fagan, M. B. (2012) · Philosophy Compass · doi:10.1111/j.1747-9991.2012.00528.x · Cited by 54
Dif-MAML: Decentralized Multi-Agent Meta-Learning
Kayaalp, M., Vlaski, S., & Sayed, A. H. (2022) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3140000 · Cited by 53 · cited 1×
“Meta-learning was also shown to be successful in a decentralized framework 76 and in combination with continual learning 77 .”
Knowledge-aware Zero-Shot Learning: Survey and Perspective
Chen, J., Geng, Y., Chen, Z., Horrocks, I., Z. Pan, J., & Chen, H. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/597 · Cited by 52
Efficient Execution of Quantized Deep Learning Models: A Compiler ApproachPreprint
Jain, A., Bhattacharya, S., Masuda, M., Sharma, V., & Wang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10226 · Cited by 50
On-device machine learning An algorithms and learning theory perspective
Dhar, S., Guo, J., Liu, J., Tripathi, S., Kurup, U., & Shah, M. (2019) · arXiv · doi:10.48550/arxiv.1911.00623 · Cited by 47
Towards Zero-Shot Learning: A Brief Review and an Attention-Based Embedding Network
Xie, G.-S., Zhang, Z., Xiong, H., Shao, L., & Li, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3208071 · Cited by 43
How Efficient Are Today’s Continual Learning Algorithms?
Harun, M. Y., Gallardo, J., Hayes, T. L., & Kanan, C. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00241 · Cited by 43 · cited 1×
“The requirement for deployment on small devices has lead to studies that measure and optimize computational loads of LL algorithms 18,44,47,119–121 , and more generally for model training with an emphasis on efficiency, for example, via quantization 122–125 .”
Continual Learning at the Edge: Real-Time Training on Smartphone Devices
Pellegrini, L., Lomonaco, V., Graffieti, G., & Maltoni, D. (2021) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2021.es2021-136 · Cited by 41
Safe Reinforcement Learning via Shielding
Alshiekh, M., Bloem, R., Ehlers, R., Könighofer, B., Niekum, S., & Topcu, U. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11797 · Cited by 37
A domain-agnostic approach for characterization of lifelong learning systems
Baker, M. M., New, A., Aguilar, M., Al-Halah, Z., Arnold, S. M. R., Ben-Iwhiwhu, E., Brna, A., Brooks, E., Brown, R. C., Daniels, Z., et al. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.007 · Cited by 37 · cited 3×
“This programme investigated both biological inspiring principles 11 and core LL algorithms, improving the understanding of algorithmic properties and metrics for evaluation 36,37 .”
Self-citationEfficient On-Device Training via Gradient Filtering
Yang, Y., Li, G., & Mărculescu, R. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00371 · Cited by 37 · cited 1×
“Category 2 is required by the on-device model training 117,118 and LL algorithms.”
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Ma, X., Jeong, S., Zhang, M., Wang, D., Choi, J., & Jeon, M. (2023) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3570361.3613297 · Cited by 37 · cited 1×
“The computational load of LL approaches is affected by the specific type of algorithm, for example, replay 126 , regularization or parameter isolation methods 32,44 , which could involve different use of CPU, GPU or memory 127 .”
Design principles for lifelong learning AI accelerators
Kudithipudi, D., Daram, A. R., Zyarah, A. M., Zohora, F. T., Aimone, J. B., Yanguas-Gil, Á., Soures, N., Neftci, E., Mattina, M., Lomonaco, V., et al. (2023) · Nature Electronics · doi:10.1038/s41928-023-01054-3 · Cited by 37 · cited 3×
“The computational load of LL approaches is affected by the specific type of algorithm, for example, replay 126 , regularization or parameter isolation methods 32,44 , which could involve different use of CPU, GPU or memory 127 .”
Self-citationTowards Federated Learning on Time-Evolving Heterogeneous DataPreprint
Guo, Y., Lin, T., & Tang, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.13246 · Cited by 37 · cited 1×
“Recently, federated learning studies have started to consider LL-related issues, such as non-IID data across locations and time 54–56 , thus identifying the need to prevent catastrophic forgetting 57,58 .”
Ten Ways to Apply Machine Learning in Earth and Space Sciences
Bortnik, J., & Camporeale, E. (2021) · Eos · doi:10.1029/2021eo160257 · Cited by 31 · cited 1×
“Space exploration has been identified as a domain in which ML can provide significant advantages 179 .”
Rethinking Pruning for Accelerating Deep Inference At the Edge
Gao, D., He, X., Zhou, Z., Tong, Y., Xu, K., & Thiele, L. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3403058 · Cited by 30 · cited 2×
“In particular, in domains where personalization and geographical variations are important, the addition of LL, multi-task or meta-learning algorithms to federated learning has become a priority 59,60 .”
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
Rostami, M. G., Isele, D., & Eaton, E. (2020) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11304 · Cited by 29
Self-citationLifelong Learning MetricsPreprint
New, A., Baker, M., Nguyen, E., & Vallabha, G. K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.08278 · Cited by 29 · cited 3×
“This programme investigated both biological inspiring principles 11 and core LL algorithms, improving the understanding of algorithmic properties and metrics for evaluation 36,37 .”
QueryPOMDP: POMDP-Based Communication in Multiagent Systems
Melo, F. S., Spaan, M. T. J., & Witwicki, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34799-3_13 · Cited by 28
Multi-Agent Active Search: A Reinforcement Learning Approach
Igoe, C., Ghods, R., & Schneider, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3131697 · Cited by 25 · cited 1×
“Multi-agent active sensing (MAAS) refers to the problem of coordinating multiple agents to strategically gather information from an underlying domain of interest to collectively achieve a desired sensing objective, for example, target detection or generative modelling of the domain 170,171 .”
Beneficial Perturbation Network for Designing General Adaptive Artificial Intelligence Systems
Wen, S., Rios, A., Ge, Y., & Itti, L. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3054423 · Cited by 24
Self-citationAn Efficient Formation Control mechanism for Multi-UAV Navigation in Remote Surveillance
Raja, G., Baskar, Y., Dhanasekaran, P., Nawaz, R., & Yu, K. (2021) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682094 · Cited by 23 · cited 1×
“MAAS is critical in many applications, from search and rescue to localization and anomaly detection in military reconnaissance problems 172 .”
Conitzer, V., & Oesterheld, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i13.26791 · Cited by 19 · cited 1×
“Multi-agent and distributed AI systems have been studied for decades 3–5 , albeit often with a focus on cooperation to solve a single task 6 or competition in game theory studies 7 .”
Wasserstein Task Embedding for Measuring Task SimilaritiesPreprint
Liu, X., Bai, Y., Lu, Y., Soltoggio, A., & Kolouri, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.11726 · Cited by 18 · cited 3×
“The assessment of task similarities 86 is also crucial when deciding what specific knowledge has to be transferred from one agent to another. research fields evolve, they expand along the edges of this abstract space to include more capabilities.”
Self-citationLightweight Learner for Shared Knowledge Lifelong Learning
Ge, Y., Li, Y., Wu, D., Xu, A., Jones, A. M., Rios, A., Fostiropoulos, I., Wen, S., Huang, P.-H., Murdock, Z. W., et al. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2305.15591 · Cited by 17 · cited 3×
“The exchange of network sub-regions via masks 94 or other suitable subsets 102,103 is also a form of transfer of partial model parameters.”
Self-citationCLR: Channel-wise Lightweight Reprogramming for Continual Learning
Ge, Y., Li, Y., Ni, S., Zhao, J., Yang, M., & Itti, L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01723 · Cited by 16 · cited 3×
“The exchange of network sub-regions via masks 94 or other suitable subsets 102,103 is also a form of transfer of partial model parameters.”
Self-citationTang, K., Wei, W.-C., Yeh, Z.-W., Hsu, T.-H., Chiu, Y.-C., Xue, C.-X., Kuo, Y.-C., Wen, T.-H., Ho, M., Lo, C., et al. (2019) · Symposium on VLSI Circuits · doi:10.23919/vlsic.2019.8778074 · Cited by 15
Lifelong Learning Without a Task Oracle
Rios, A., & Itti, L. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00049 · Cited by 13 · cited 1×
“Understanding similarities among datasets 85,86 and tasks is, therefore, an emerging field that could empower knowledge reuse, help knowledge organization, detect exceptions or uncertainty 87–89 , and learn without an oracle 86,90 .”
Self-citationDivide-and-conquer the NAS puzzle in resource-constrained federated learning systems
Venkatesha, Y., Kim, Y., Park, H., & Panda, P. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.10.006 · Cited by 11
Self-citationBayer, T. J. (2007) · AIAA SPACE Conference & Exposition · doi:10.2514/6.2007-6109 · Cited by 10 · cited 1×
“For example, with a round-trip light-time of 6 to 40 minutes 184 , communication to Mars and beyond is severely limited.”
Bhattacharjee, A., Venkatesha, Y., Moitra, A., & Panda, P. (2022) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3489517.3530473 · Cited by 10
Self-citationInternational Workshop on Federated Learning for Distributed Data Mining
Hong, J., Zhu, Z., Lyu, L., Zhou, Y., Boddeti, V. N., & Zhou, J. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599198 · Cited by 10
Sharing Lifelong Reinforcement Learning Knowledge via Modulating MasksPreprint
Nath, S., Peridis, C., Ben-Iwhiwhu, E., Liu, X., Dora, S., Liu, C., Kolouri, S., & Soltoggio, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.10997 · Cited by 10 · cited 3×
“The exchange of network sub-regions via masks 94 or other suitable subsets 102,103 is also a form of transfer of partial model parameters.”
Self-citationProjected Latent Distillation for Data-Agnostic Consolidation in distributed continual learning
Carta, A., Cossu, A., Lomonaco, V., Bacciu, D., & van de Weijer, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127935 · Cited by 10
Learning a Shield from Catastrophic Action Effects: Never Repeat the Same MistakePreprint
Shperberg, S., Liu, B., & Stone, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.09516 · Cited by 8 · cited 1×
“The advantage of a collective of robots that share risks to maintain safety has been explored previously 166,167 .”
Self-citationCoDeC: Communication-Efficient Decentralized Continual Learning
Choudhary, S., Aketi, S. A., Saha, G., & Roy, K. (2024) · Transactions on machine learning research · doi:10.48550/arxiv.2303.15378 · Cited by 8 · cited 1×
“A similar concept is also exploited in other studies 102,103,148–150 , where task-agnostic backbones are combined with small sets of task-specific parameters that allow for knowledge transfer with minimal changes to a model 151,152 .”
Self-citationCollaborative Learning Through Shared Collective Knowledge and Local Expertise
Mohammadi, J., & Kolouri, S. (2019) · Machine learning for signal processing ... · doi:10.1109/mlsp.2019.8918888 · Cited by 7 · cited 1×
“A following study 145 improves upon the COLLA approach to allow each agent to maintain local agent-specific skills in addition to sharing collective knowledge.”
Self-citationMulti-Agent Lifelong Implicit Neural Learning
Kolouri, S., Abbasi, A., Koohpayegani, S. A., Nooralinejad, P., & Pirsiavash, H. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3338092 · Cited by 6
Self-citationPRANC: Pseudo RAndom Networks for Compacting deep models
Nooralinejad, P., Abbasi, A., Koohpayegani, S. A., Pourahmadi, K., Khan, R. M. S., Kolouri, S., & Pirsiavash, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01561 · Cited by 6
Self-citationChen, Z., & Liu, B. (2018) · Synthesis lectures on artificial intelligence and machine learning · doi:10.1007/978-3-031-01581-6_1 · Cited by 4
Zheng, G., Lai, S., Braverman, V., Jacobs, M. A., & Parekh, V. S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.05310 · Cited by 4 · cited 1×
“A previous study 163 demonstrates the use of deep reinforcement learning on edge devices to continually learn and adapt to changing medical imaging environments and adjust to low-compute devices.”
Self-citationUSC-DCT: A Collection of Diverse Classification Tasks
Jones, A. M., Sahin, G., Murdock, Z. W., Ge, Y., Xu, A., Li, Y., Wu, D. J., Ni, S., Huang, P.-H., Lekkala, K. K., et al. (2023) · Data · doi:10.3390/data8100153 · Cited by 3 · cited 1×
“Understanding similarities among datasets 85,86 and tasks is, therefore, an emerging field that could empower knowledge reuse, help knowledge organization, detect exceptions or uncertainty 87–89 , and learn without an oracle 86,90 .”
Self-citationAutonomous Exploration for Gathering Increased Science
Bornstein, B., Castaño, R., Estlin, T. A., Gaines, D. M., Anderson, R. C., Thompson, D. R., deGranville, C. K., Chien, S., Tang, B., Burl, M. C., et al. (2010) · NASA Technical Reports Server (NASA) · Cited by 2
Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual LearningPreprint
Carta, A., Cossu, A., Lomonaco, V., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.15888 · Cited by 1 · cited 1×
“However, recent studies have shown that synthetic and privacy-preserving can be used 159,160 .”
Multi-environment lifelong deep reinforcement learning for medical imaging
Zheng, G., Lai, S., Braverman, V., Leung, D., Jacobs, M. A., & Parekh, V. S. (2026) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi69079.2026.00138 · Cited by 1 · cited 1×
“In such a context, ShELL agents that can asynchronously share experiences with each other to collectively learn multiple tasks over time offer a significant advantage over centralized single-task models 164 .”
Self-citation2022 roadmap on neuromorphic computing and engineering
Christensen, D. V., Dittmann, R., Linares-Barranco, B., Sebastian, A., Le Gallo, M., Redaelli, A., Slesazeck, S., Mikolajick, T., Spiga, S., Menzel, S., et al. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4a83
Self-citation
Research works printed but not linked: 31
- Ferber, J. & Weiss, G. Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence Vol. 1 (Addison-Wesley, 1999).
- Mendez, J. A., van Seijen, H. & Eaton, E. Modular lifelong reinforcement learning via neural composition. In International Conference on Learning Representations (2022).
- Li, T., Sahu, A. K., Talwalkar, A. & Smith, V. Federated learning: challenges, methods, and future directions. IEEE Signal Process. Mag. 37, 50–60 (2020).
- Zhang, J., Cheung, B., Finn, C., Levine, S. & Jayaraman, D. Cautious adaptation for reinforcement learning in safety-critical settings. In International Conference on Machine Learning 11055–11065 (PMLR, 2020).
- McMahan, B., Moore, E., Ramage, D., Hampson, S. & Arcas, B. A. Y. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics 1273–1282, (PMLR, 2017).
- Silver, D. L., Yang, Q. & Li, L. Lifelong machine learning systems: beyond learning algorithms. In 2013 AAAI Spring Symposium Series (AAAI, 2013).
- Mendez, J. A. & Eaton, E. Lifelong learning of compositional structures. In International Conference on Learning Representations (2021).
- Xie, A. & Finn, C. Lifelong robotic reinforcement learning by retaining experiences. In Conference on Lifelong Learning Agents 838–855 (PMLR, 2022).
- Ben-Iwhiwhu, E., Nath, S., Pilly, P. K., Kolouri, S. & Soltoggio, A. Lifelong reinforcement learning with modulating masks. In Transactions on Machine Learning Research (2023).
- Tasse, G. N., James, S. & Rosman, B. Generalisation in lifelong reinforcement learning through logical composition. In International Conference on Learning Representations (2022).
- De Lange, M., van de Ven, G. & Tuytelaars, T. Continual evaluation for lifelong learning: identifying the stability gap. In 11th International Conference on Learning Representations https://openreview.net/forum?id=Zy350cRstc6 (ICLR, 2023).
- Yoon, J., Jeong, W., Lee, G., Yang, E. & Hwang, S. J. Federated continual learning with weighted inter-client transfer. In International Conference on Machine Learning 12073–12086 (PMLR, 2021).
- Taylor, M. E. & Stone, P. Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633–1685 (2009).
- Koohpayegani, S. A., Navaneet, K., Nooralinejad, P., Kolouri, S. & Pirsiavash, H. NOLA: networks as linear combination of low rank random basis. In International Conference on Learning Representations (ICLR, 2024).
- Musliner, D. J. et al. OpenMIND: planning and adapting in domains with novelty. In Proc. 9th Conference on Advances in Cognitive Systems (2021).
- Mendez, J. & Eaton, E. How to reuse and compose knowledge for a lifetime of tasks: a survey on continual learning and functional composition. In Transactions on Machine Learning Research (2023).
- Zoph, B. & Le, Q. Neural architecture search with reinforcement learning. In International Conference on Learning Representations (2017).
- Lin, J. et al. On-device training under 256kb memory. 36th Conference on Neural Information Processing Systems (NeurIPS)(2022).
- Hayes, T. L. & Kanan, C. Online continual learning for embedded devices. In Proc. First Conference on Lifelong Learning Agents (eds Chandar, S. et al.) 744–766 (PMLR, 2022).
- Rostami, M., Kolouri, S., Kim, K. & Eaton, E. Multi-agent distributed lifelong learning for collective knowledge acquisition. In Proc. 17th International Conference on Autonomous Agents and Multiagent Systems 2018 (2017).
- Koster, N., Grothe, O. & Rettinger, A. Signing the supermask: keep, hide, invert. In International Conference on Learning Representations https://openreview.net/forum?id=e0jtGTfPihs (2022).
- Saha, G., Garg, I. & Roy, K. Gradient projection memory for continual learning. In International Conference on Learning Representations (2021).
- Singh, P., Verma, V. K., Mazumder, P., Carin, L. & Rai, P. Calibrating CNNs for lifelong learning. Adv. Neural Inf. Process. Syst. 33, 15579–15590 (2020).
- Ma, Z., Lu, Y., Li, W. & Cui, S. EFL: elastic federated learning on non-IID data. In Conference on Lifelong Learning Agents 92–115 (PMLR, 2022).
- Baradad Jurjo, M., Wulff, J., Wang, T., Isola, P. & Torralba, A. Learning to see by looking at noise. Adv. Neural Inf. Process. Syst. 34, 2556–2569 (2021).
- Zheng, G., Zhou, S., Braverman, V., Jacobs, M. A. & Parekh, V. S. Selective experience replay compression using coresets for lifelong deep reinforcement learning in medical imaging. In Proc. Machine Learning Research 227, 1751–1764 (2024).
- Shperberg, S. S., Liu, B., Allievi, A. & Stone, P. A rule-based shield: Accumulating safety rules from catastrophic action effects. In Conference on Lifelong Learning Agents 231–242 (PMLR, 2022).
- Garcıa, J. & Fernández, F. A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437–1480 (2015).
- Sitzmann, V., Martel, J., Bergman, A., Lindell, D. & Wetzstein, G. Implicit neural representations with periodic activation functions. Adv. Neural Inf. Process. Syst. 33, 7462–7473 (2020).
- Bylow, E., Sturm, J., Kerl, C., Kahl, F. & Cremers, D. Real-time camera tracking and 3D reconstruction using signed distance functions. Rob. Sci. Syst. 2, 2 (2013).
- Kozik, R., Choras, M. & Keller, J. Balanced efficient lifelong learning (B-ELLA) for cyber attack detection. J. Univers. Comput. Sci. 25, 2–15 (2019).
Cited by
A survey on knowledge distillation: Recent advancements
Moslemi, A., Briskina, A., Dang, Z., & Li, J. H. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100605 · Cited by 239
Upadhyay, R., Phlypo, R., Saini, R., & Liwicki, M. (2024) · IEEE Access · doi:10.1109/access.2024.3478805 · Cited by 56
“…techniques in ML or Deep Learning (DL), such as transfer learning [3], [4], meta-learning [5], [6], [7], Multi-Task Learning (MTL) [8], [9], [10], [11], and lifelong learning [12], [13], are inspired by such human capability, where the aim is to transfer the learning of one task to another.”
BackgroundMethodScaling Up Multi-Agent Reinforcement Learning: An Extensive Survey on Scalability Issues
Liu, D., Ren, F., Yan, J. H., Su, G., Gu, W., & Kato, S. (2024) · IEEE Access · doi:10.1109/access.2024.3410318 · Cited by 66
“By leveraging various intermediate learning signals under different learning stages and strategies, it is possible to develop a scalable, resilient and sustainable lifelong learning paradigm that accepts multiple types of inter-and intra-agent knowledge [121], as explored by Soltoggio et al. [135].”
BackgroundDesigning AI-powered learning: adult learners’ expectations for curriculum and human-AI interaction
Kim, J., Yu, S., Detrick, R., Lin, X. Y., & Li, N. (2025) · Educational Technology Research and Development · doi:10.1007/s11423-025-10549-z · Cited by 47
“AI-powered tools could additionally support continuous lifelong learning by staying current with new information, industry trends, and technological advances (Poquet & de Laat, 2021; Soltoggio et al., 2024).”
Ji, Z., & Jiang, M. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.116159 · Cited by 53
Metadata
- Authors
- Soltoggio, A., Ben-Iwhiwhu, E., Braverman, V., Eaton, E., Epstein, B., Ge, Y., Halperin, L., How, J., Itti, L., Jacobs, M. A., Kantharaju, P., Le, L., Lee, S., Liu, X., Monteiro, S. T., Musliner, D., Nath, S., Panda, P., Peridis, C., Pirsiavash, H., Parekh, V., Roy, K., Shperberg, S., Siegelmann, H. T., Stone, P., Vedder, K., Wu, J., Yang, L., Zheng, G., & Kolouri, S.
- Affiliations
- Loughborough University (GB)
- Rice University (US)
- University of Pennsylvania (US)
- ECS (United States) (US)
- University of Southern California (US)
- Massachusetts Institute of Technology (US)
- Johns Hopkins University (US)
- Smart Information Flow Technologies (United States) (US)
- Aurora Flight Sciences (United States) (US)
- Vanderbilt University (US)
- Yale University (US)
- University of California, Davis (US)
- University of Maryland, Baltimore (US)
- Purdue University West Lafayette (US)
- Ben-Gurion University of the Negev (IL)
- University of Massachusetts Amherst (US)
- The University of Texas at Austin (US)
- University of California, Berkeley (US)
- University of California, Los Angeles (US)
- Corresponding author
- Soltoggio, Andrea
- ORCID
- Soltoggio, Andrea
- Ben-Iwhiwhu, Eseoghene
- Braverman, Vladimir
- Eaton, Eric
- Epstein, Benjamin
- Ge, Yunhao
- How, Jonathan
- Itti, Laurent
- Jacobs, Michael A.
- Kantharaju, Pavan
- Le, Long
- Lee, Steven
- Liu, Xinran
- Monteiro, Sildomar T.
- Musliner, David
- Nath, Saptarshi
- Panda, Priyadarshini
- Pirsiavash, Hamed
- Parekh, Vishwa
- Roy, Kaushik
- Shperberg, Shahaf
- Siegelmann, Hava T.
- Stone, Peter
- Wu, Jingfeng
- Yang, Lin
- Kolouri, Soheil
- Venue
- Nature Machine Intelligence
- Published
- 2024-03-22
- Volume
- 6
- Issue
- 3
- Pages
- 251-264
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W4393097270
- Cited by
- 51
- References
- 173
- Citations by year
- 2026: 18 · 2025: 26 · 2024: 7
- FWCI
- 6.60
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Licence
- cc-by
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Nature Machine Intelligence (publishedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- United States Department of Defense | Defense Advanced Research Projects Agency (HR00112190132, HR00112190135, HR00112190130, HR00112190133, HR00112190134, HR00112190136)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- lifelong learning, knowledge sharing, edge computing, multi-agent systems, decentralized learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.