Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
Open accessThe DOI matches its Crossref record; 70 of the 70 references it cites were found in a registry or an index.
Abstract
Federated learning has emerged as a promising paradigm for privacy-preserving collaboration among different parties. Recently, with the popularity of federated learning, an influx of approaches have delivered towards different realistic challenges. In this survey, we provide a systematic overview of the important and recent developments of research on federated learning. First, we introduce the study history and terminology definition of this area. Then, we comprehensively review three basic lines of research: generalization, robustness, and fairness, by introducing their respective background concepts, task settings, and main challenges. We also offer a detailed overview of representative literature on both methods and datasets. We further benchmark the reviewed methods on several well-known datasets. Finally, we point out several open issues in this field and suggest opportunities for further research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
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 · cited 1×
“Pioneering works [69], [71], [74], [76], [86] basically focus on the conceptual framework and macro guidance and neglect in-depth exploration of specific challenges and problems.”
BackgroundSelf-citationTowards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · cited 2×
“Pioneering works [69], [71], [74], [76], [86] basically focus on the conceptual framework and macro guidance and neglect in-depth exploration of specific challenges and problems.”
BackgroundFashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Huang, X., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.167 · Cited by 5,076
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016) · arXiv · doi:10.48550/arxiv.1612.01474 · Cited by 3,666
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
The EU General Data Protection Regulation (GDPR)
Voigt, P., & von dem Bussche, A. (2017) · doi:10.1007/978-3-319-57959-7 · Cited by 3,001
Federated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077
Buciluǎ, C., Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150464 · Cited by 2,068
On the Convergence of FedAvg on Non-IID Data
Li, X., Huang, K., Yang, W., Wang, S., & Zhang, Z. (2019) · arXiv · doi:10.48550/arxiv.1907.02189 · Cited by 1,575 · cited 2×
“However, these solutions typically assume that each client distribution obeys the independent and identically distributed property, which does not hold for the heterogeneous federated learning setting [26], [68], [95], [283].”
BackgroundHow to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · cited 6×
“Recently, advanced attacks focus on the fixed-trigger backdoor paradigm [53], [54], [105], [141], [142], [143] and trigger-optimization backdoor solution [55], [144], [145], [146], [147], [148] to evade the secure detection strategies.”
BackgroundInfluentialA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., & He, B. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3124599 · Cited by 1,407
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Concrete Problems in AI Safety
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016) · arXiv · doi:10.48550/arxiv.1606.06565 · Cited by 1,314
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238 · cited 3×
“Traditional attack strategies often involve predefined and static behaviors, such as the use of Symmetry Flipping in Byzantine Attack [45], fixed trigger patterns in Backdoor Attack [43], [52], [54], and random weight in Free Rider Attack [131].”
BackgroundHuang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2011) · Proceedings of the 4th ACM workshop on Security and artificial intelligence · doi:10.1145/2046684.2046692 · Cited by 1,194 · cited 5×
“…uploads the modified information to inhibit federated convergence and performance from the data-based and parameter-based angles. i) Data-Based Byzantine Attack: As for the data-based attacks [41], [42], malicious clients would intentionally pollute the local data to corrupt the learned model.”
BackgroundInfluentialFederated Learning for Mobile Keyboard Prediction
Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., Eichner, H., Kiddon, C., & Ramage, D. (2018) · arXiv · doi:10.48550/arxiv.1811.03604 · Cited by 1,148
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130
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
Generalizing to unseen domains: A survey on domain generalization
Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Chen, Y., Zeng, W., & Yu, P. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3178128 · Cited by 1,046
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017) · arXiv · doi:10.48550/arxiv.1712.05526 · Cited by 1,039
FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
Cao, X., Fang, M., Liu, J., & Gong, N. Z. (2021) · Proceedings 2021 Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24434 · Cited by 999
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Ovadia, Y., Fertig, E., Ren, J., Nado, Z., Sculley, D., Nowozin, S., Dillon, J. V., Lakshminarayanan, B., & Snoek, J. (2019) · arXiv · doi:10.48550/arxiv.1906.02530 · Cited by 989
Arjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019) · arXiv · doi:10.48550/arxiv.1907.02893 · Cited by 927 · cited 1×
“…andprovidethefollowingdefinition: (5) • Distinguish Out-Client Shift and Domain Generalization: Domain generalization (DG) [117], [118], [119], [120], [121], [122], [123], [124], [125], [126], [127] focuses on enhancing the…”
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
Wang, J., Liu, Q., Liang, H., Joshi, G., & Poor, H. V. (2020) · arXiv · doi:10.48550/arxiv.2007.07481 · Cited by 927 · cited 1×
“The isolated data distributions are often non-independent and non-identically distributed (non-IID), reflecting local distribution differences among clients [27], [38], [112], [113], [114].”
BackgroundAdaptive Federated Optimization
Reddi, S., Charles, Z., Zaheer, M., Garrett, Z., Rush, K., Konečný, J., Kumar, S., & McMahan, H. B. (2020) · arXiv · doi:10.48550/arxiv.2003.00295 · Cited by 840 · cited 1×
“Another stream investigates the server-side optimizing objective, including gradient-biased server optimizer [195] and global local joint objectives [239], [240], [241].”
BackgroundAnil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.10403 · Cited by 834
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Fang, M., Cao, X., Jia, J., & Gong, N. Z. (2019) · arXiv · doi:10.48550/arxiv.1911.11815 · Cited by 828 · cited 3×
“…data, i.e., Data-Based Byzantine Attack [45], [46] and directly manipulating the model parameters, Model-Based Byzantine Attack [47], [48], [49] i) Backdoor Attack: evils inject the backdoor trigger to induce the global model to learn misleading information, so as to predict…”
BackgroundMethodThe Hidden Vulnerability of Distributed Learning in Byzantium
Mhamdi, E. M. E., Guerraoui, R., & Rouault, S. (2018) · arXiv · doi:10.48550/arxiv.1802.07927 · Cited by 648
A secure federated transfer learning framework
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2988525 · Cited by 645
Self-citationSecure Federated Transfer Learning
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2018) · arXiv · doi:10.48550/arxiv.1812.03337 · Cited by 645
Self-citationYang (2019) · doi:10.1145/3339474 · Cited by 632
Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses for Federated Learning
Shejwalkar, V., & Houmansadr, A. (2021) · Proceedings 2021 Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24498 · Cited by 615 · cited 4×
“Building upon the attack goals, Byzantine Attack primarily focuses on untargeted disruptions, aiming to hinder the global model convergence or to degrade federated performance [44], [47], [49], [137].”
BackgroundMethodInfluentialPrivacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548 · cited 1×
“III) Fair Federated Learning (FFL): Fairness in federated learning mainly encompasses two aspects [57], [81], [107].”
BackgroundSelf-citationFair Resource Allocation in Federated Learning
Li, T., Sanjabi, M., Beirami, A., & Smith, V. (2019) · arXiv · doi:10.48550/arxiv.1905.10497 · Cited by 475
Jeong, E., Oh, S., Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1811.11479 · Cited by 465 · cited 1×
“Asurgeofeffortssupplementslocaldata tomimictheidealdatadistributionviathebatchnormalization layer[205],[206],MixUp[186],[207],[208],[209],[210], datagenerativegenerator[205],[211].”
Lyu, L., Yu, H., Zhao, J., & Yang, Q. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_1 · Cited by 444
Self-citationHuang, L., Shea, A. L., Qian, H., Masurkar, A., Deng, H., & Liu, D. (2019) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103291 · Cited by 437
Attack of the tails: Yes, you really can backdoor federated learning
Wang, H., Sreenivasan, K., Rajput, S., Vishwakarma, H., Agarwal, S., Sohn, J.-Y., Lee, K., & Papailiopoulos, D. (2020) · arXiv · doi:10.48550/arxiv.2007.05084 · Cited by 406
Federated learning enables big data for rare cancer boundary detection
Pati, S., Baid, U., Edwards, B., Sheller, M., Wang, S.-H., Reina, G. A., Foley, P., Gruzdev, A., Karkada, D., Davatzikos, C., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-33407-5 · Cited by 394
Mitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385
Can You Really Backdoor Federated Learning?
Sun, Z., Kairouz, P., Suresh, A. T., & McMahan, H. B. (2019) · arXiv · doi:10.48550/arxiv.1911.07963 · Cited by 348 · cited 4×
“Backdoor Attack seeks to compromise accuracy on specific test inputs while maintaining high accuracy on the original evaluation distribution [53], [54], [104], [135].”
BackgroundInfluentialItahara, S., Nishio, T., Koda, Y., Morikura, M., & Yamamoto, K. (2020) · arXiv · doi:10.48550/arxiv.2008.06180 · Cited by 338
Itahara, S., Nishio, T., Koda, Y., Morikura, M., & Yamamoto, K. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3070013 · Cited by 338 · cited 1×
“Current solutions normally leverage the labeled samples for the warm-up operation [68], [184] and unlabeled instances for distillation [204] and pretraining [185] strategies.”
BackgroundRodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296
Nguyen (2022) · doi:10.1145/3453476 · Cited by 286
Unifying distillation and privileged information
Lopez-Paz, D., Bottou, L., Schölkopf, B., & Vapnik, V. (2015) · arXiv · doi:10.48550/arxiv.1511.03643 · Cited by 270 · cited 1×
“…focuses on server-side fine-tuning by synthesizing relevant information to facilitate empirical risk minimization [194], [229], [230], [231], [232], [233] or conducting the knowledge distillation on public dataset for knowledge transferring [192], [193], [196], [234], [235], [236], [237], [238].”
BackgroundIncentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
Kang, J., Xiong, Z., Niyato, D., Yu, H., Liang, Y.-C., & Kim, D. I. (2019) · 2019 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS) · doi:10.1109/vts-apwcs.2019.8851649 · Cited by 255
Towards Fair and Privacy-Preserving Federated Deep Models
Lyu, L., Yu, J., Nandakumar, K., Li, Y., Ma, X., Jin, J., Yu, H., & Ng, K. S. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.2996273 · Cited by 250 · cited 3×
“Contribution evaluation plays a crucial role in federated learning by assessing each client’s contribution in a privacy-friendly manner [56], [308].”
BackgroundDuan, M., Liu, D., Chen, X., Tan, Y., Ren, J., Qiao, L., & Liang, L. (2019) · arXiv · doi:10.48550/arxiv.1907.01132 · Cited by 250
Duan, M., Liu, D., Chen, X., Tan, Y., Ren, J., Qiao, L., & Liang, L. (2019) · 2019 IEEE 37th International Conference on Computer Design (ICCD) · doi:10.1109/iccd46524.2019.00038 · Cited by 250
Threats to federated learning A survey
Lyu, L., Yu, H., & Yang, Q. (2020) · arXiv · doi:10.48550/arxiv.2003.02133 · Cited by 221
Self-citationProvably Secure Federated Learning against Malicious Clients
Cao, X., Jia, J., & Gong, N. Z. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16849 · Cited by 141
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
Liao, C., Zhong, H., Squicciarini, A., Zhu, S., & Miller, D. (2018) · arXiv · doi:10.48550/arxiv.1808.10307 · Cited by 110
Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning
Sun, J., Chen, T., Giannakis, G. B., Yang, Q., & Yang, Z. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3033286 · Cited by 102
Self-citationFree-rider attacks on model aggregation in federated learning
Fraboni, Y., Vidal, R., & Lorenzi, M. (2020) · arXiv · doi:10.48550/arxiv.2006.11901 · Cited by 97
Free-riders in Federated Learning: Attacks and Defenses
Lin, J., Du, M., & Liu, J. (2019) · arXiv · doi:10.48550/arxiv.1911.12560 · Cited by 76 · cited 6×
“1) Outlier Parameter Detection: The stream of solutions focuses on detecting the outlier of model parameters to mitigate the free rider effect [131], [294].”
BackgroundInfluentialHow to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
Lyu, L., Li, Y., Nandakumar, K., Yu, J., & Ma, X. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3006287 · Cited by 31
Defending against Backdoors in Federated Learning with Robust Learning Rate
Ozdayi, M. S., Kantarcioglu, M., & Gel, Y. R. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i10.17118 · Cited by 30
Robust federated learning with attack-adaptive aggregation
Wan, C. P. (2022) · doi:10.14711/thesis-991012994506603412 · Cited by 24 · cited 1×
“2) Statistics Distribution Tolerance: A handful of robust aggregation schemes focus on constructing diverse statistical criteria to select the circumvent the evil clients [44], [268], [269], [275].”
Background
Metadata
- Authors
- Huang, W., Ye, M., Shi, Z., Wan, G., Li, H., Du, B., & Yang, Q.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2024-12
- Volume
- 46
- Issue
- 12
- Pages
- 9387-9406
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4399995632
- Cited by
- 232
- References
- 70
- FWCI
- 34.53
- Type
- journal article
- Language
- en
- Open access
- green
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.