CoChat

A collective AI via lifelong learning and sharing at the edge

Open access

The DOI matches its Crossref record; 181 of the 181 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

Crossref · 10.1038/s42256-024-00800-2

Cites

181 of 181 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 181 references

Research works printed but not linked: 31

  1. Ferber, J. & Weiss, G. Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence Vol. 1 (Addison-Wesley, 1999).
  2. Mendez, J. A., van Seijen, H. & Eaton, E. Modular lifelong reinforcement learning via neural composition. In International Conference on Learning Representations (2022).
  3. Li, T., Sahu, A. K., Talwalkar, A. & Smith, V. Federated learning: challenges, methods, and future directions. IEEE Signal Process. Mag. 37, 50–60 (2020).
  4. 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).
  5. 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).
  6. Silver, D. L., Yang, Q. & Li, L. Lifelong machine learning systems: beyond learning algorithms. In 2013 AAAI Spring Symposium Series (AAAI, 2013).
  7. Mendez, J. A. & Eaton, E. Lifelong learning of compositional structures. In International Conference on Learning Representations (2021).
  8. Xie, A. & Finn, C. Lifelong robotic reinforcement learning by retaining experiences. In Conference on Lifelong Learning Agents 838–855 (PMLR, 2022).
  9. 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).
  10. Tasse, G. N., James, S. & Rosman, B. Generalisation in lifelong reinforcement learning through logical composition. In International Conference on Learning Representations (2022).
  11. 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).
  12. 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).
  13. Taylor, M. E. & Stone, P. Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633–1685 (2009).
  14. 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).
  15. Musliner, D. J. et al. OpenMIND: planning and adapting in domains with novelty. In Proc. 9th Conference on Advances in Cognitive Systems (2021).
  16. 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).
  17. Zoph, B. & Le, Q. Neural architecture search with reinforcement learning. In International Conference on Learning Representations (2017).
  18. Lin, J. et al. On-device training under 256kb memory. 36th Conference on Neural Information Processing Systems (NeurIPS)(2022).
  19. 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).
  20. 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).
  21. 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).
  22. Saha, G., Garg, I. & Roy, K. Gradient projection memory for continual learning. In International Conference on Learning Representations (2021).
  23. 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).
  24. 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).
  25. 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).
  26. 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).
  27. 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).
  28. Garcıa, J. & Fernández, F. A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437–1480 (2015).
  29. 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).
  30. 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).
  31. 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

See all 56

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
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
Licence
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A collective AI via lifelong learning and sharing at the edge. https://app.cochat.ai/papers/10.1038/s42256-024-00800-2
The paper
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., . . . Kolouri, S. (2024). A collective AI via lifelong learning and sharing at the edge. Nature Machine Intelligence. https://doi.org/10.1038/s42256-024-00800-2

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.