The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
Open accessAbstract
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential for catastrophic forgetting across real-world heterogeneous devices. In this paper, we demonstrate that self-attention-based architectures (e.g., Transformers) are more robust to distribution shifts and hence improve federated learning over heterogeneous data. Concretely, we conduct the first rigorous empirical investigation of different neural architectures across a range of federated algorithms, real-world benchmarks, and heterogeneous data splits. Our experiments show that simply replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices, accelerate convergence, and reach a better global model, especially when dealing with heterogeneous data. We release our code and pretrained models to encourage future exploration in robust architectures as an alternative to current research efforts on the optimization front.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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
Self-citationGradient-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
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
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
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 1×
“Therefore, it provides an opportunity for collaborative machine learning across multiple institutions without risking leakage of private data [25,36,54].”
BackgroundEmerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“If large-scale pretraining datasets are not available, self-supervised pretraining [6, 18] could be an alternative.”
BackgroundFederated 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
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×
“Therefore, it provides an opportunity for collaborative machine learning across multiple institutions without risking leakage of private data [25,36,54].”
BackgroundThe 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
Multimodal Transformer for Unaligned Multimodal Language Sequences
Tsai, Y.-H. H., Bai, S., Liang, P. P., Kolter, J. Z., Morency, L.-P., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1656 · Cited by 2,259 · cited 2×
“This property has led to the prevalence of Transformers in self-supervised learning where heterogeneity is manifested via distribution shifts between unlabeled pretraining data and labeled test data [11], as well as in multimodal learning over fundamentally heterogeneous input modalities such as image and text [24, 60…”
BackgroundSelf-citationSheller, 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 3×
“Prior research has shown that training FL models with FedAVG or CWT incurs issues such as weight divergence and catastrophic forgetting respectively [28, 53].”
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 · cited 2×
“) due to different medical imaging protocols [16,55], as well as in natural data splits due to user idiosyncrasies in speaking [33], typing [17], and writing [28].”
BackgroundParmar, N., Vaswani, A., Uszkoreit, J., Kaiser, Ł., Shazeer, N., Ku, A., & Tran, D. (2018) · arXiv · doi:10.48550/arxiv.1802.05751 · Cited by 1,085 · cited 1×
“[50] applied self-attention to local neighborhoods of an image while the Vision Transformer (ViT) [12] achieved stateof-the-art on ImageNet classification by directly applying Transformers with global self-attention to full-sized images.”
MethodGenerating Long Sequences with Sparse Transformers
Child, R., Gray, S., Radford, A., & Sutskever, I. (2019) · arXiv · doi:10.48550/arxiv.1904.10509 · Cited by 1,063
Federated learning of predictive models from federated Electronic Health Records
Brisimi, T. S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I. C., & Shi, W. (2018) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2018.01.007 · Cited by 997 · cited 1×
“This has proved especially useful in domains such as healthcare [4, 7, 15, 40], learning from mobile devices [17, 38], s-”
BackgroundStand-Alone Self-Attention in Vision Models
Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019) · arXiv · doi:10.48550/arxiv.1906.05909 · Cited by 977 · cited 1×
“On the other hand, ViTs use self-attention to learn global interactions [53] and have been shown to be less biased towards local patterns as compared to CNNs.”
BackgroundFederated Learning for Wireless Communications: Motivation, Opportunities, and Challenges
Niknam, S., Dhillon, H. S., & Reed, J. H. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.1900461 · Cited by 820 · cited 1×
“mart cities [25], and communication networks [49], where preserving privacy is crucial.”
BackgroundSplit learning for health: Distributed deep learning without sharing raw patient data
Vepakomma, P., Gupta, O., Swedish, T., & Raskar, R. (2018) · arXiv · doi:10.48550/arxiv.1812.00564 · Cited by 513 · cited 1×
“way (such as Cyclic Weight Transfer (CWT) [7] and Split learning [62]).”
MethodLyu, 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 · cited 1×
“FL could also be sensitive to external security attacks from adversaries [38].”
BackgroundUnderstanding Robustness of Transformers for Image Classification
Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., & Veit, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01007 · Cited by 440 · cited 4×
“Due to its sequential and serial training strategy, training CNNs in a CWT paradigm usually results in catastrophic forgetting on non-IID data partitions: the model’s performance on previous clients abruptly degrades after a few updates on a new client with a different data distribution [3, 48].”
BackgroundInfluentialIntriguing Properties of Vision Transformers
Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F. S., & Yang, M.-H. (2021) · arXiv · doi:10.48550/arxiv.2105.10497 · Cited by 431 · cited 3×
“…Due to its sequential and serial training strategy, training CNNs in a CWT paradigm usually results in catastrophic forgetting on non-IID data partitions: the model’s performance on previous clients abruptly degrades after a few updates on a new client with a different data distribution [3, 48].”
BackgroundLearning Robust Global Representations by Penalizing Local Predictive Power
Wang, H., Ge, S., Xing, E. P., & Lipton, Z. C. (2019) · arXiv · doi:10.48550/arxiv.1905.13549 · Cited by 337
Vision Transformers Are Robust Learners
Paul, S., & Chen, P.-Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20103 · Cited by 244 · cited 1×
“Among several particularly relevant findings are that ViTs are highly robust to severe occlusions, perturbations, domain shifts [3, 48], as well as synthetic and natural adversarial examples [44,51].”
BackgroundRe-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
Hsu, Y.-C., Liu, Y.-C., Ramasamy, A., & Kira, Z. (2018) · arXiv · doi:10.48550/arxiv.1810.12488 · Cited by 211 · cited 3×
“We further compare ViT(S)-CWT with an optimization method specifically designed to alleviate catastrophic forgetting, EWC [30] (using the implementation from [23]).”
BackgroundMethodResultFederated Learning for Breast Density Classification: A Real-World Implementation
Roth, H. R., Chang, K., Singh, P., Neumark, N., Li, W., Gupta, V., Gupta, S., Qu, L., Ihsani, A., Bizzo, B. C., et al. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-60548-3_18 · Cited by 202
Self-citationGuo, P., Wang, P., Zhou, J., Jiang, S., & Patel, V. M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00245 · Cited by 193 · cited 1×
“This has proved especially useful in domains such as healthcare [4, 7, 15, 40], learning from mobile devices [17, 38], s-”
Background
Cited by
Yan, R., Qu, L., Wei, Q., Huang, S.-C., Shen, L., Rubin, D. L., Xing, L., & Zhou, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3233574 · Cited by 183
Self-citationApplications of Federated Learning; Taxonomy, Challenges, and Research Trends
Shaheen, M., Farooq, M. S., Umer, T., & Kim, B.-S. (2022) · Electronics · doi:10.3390/electronics11040670 · Cited by 157
Adam, M., & Baroudi, U. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3506214 · Cited by 46
Yue, G., Wei, P., Zhou, T., Song, Y., Zhao, C., Wang, T., & Lei, B. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3319516 · Cited by 24
Optimal Adaptive Power Control for Over-The-Air Federated Edge Learning Under Fading Channels
Yu, X., Xiao, B., Ni, W., & Wang, X. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3283790 · Cited by 19
Metadata
- Authors
- Qu, L., Zhou, Y., Liang, P. P., Xia, Y., Wang, F., Adeli, E., Fei-Fei, L., & Rubin, D.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Volume
- 2022
- Pages
- 10051-10061
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312352414
- Cited by
- 200
- References
- 33
- FWCI
- 25.31
- Type
- conference paper
- 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.