Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia, Feifei Wang, Ehsan Adeli, Li Fei-Fei, Daniel Rubin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 10061-10071

Abstract


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 will release our code and pretrained models to encourage future exploration in robust architectures as an alternative to current research efforts on the optimization front.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2022_CVPR, author = {Qu, Liangqiong and Zhou, Yuyin and Liang, Paul Pu and Xia, Yingda and Wang, Feifei and Adeli, Ehsan and Fei-Fei, Li and Rubin, Daniel}, title = {Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10061-10071} }