Revisiting Weighted Aggregation in Federated Learning with Neural Networks

Zexi Li, Tao Lin, Xinyi Shang, Chao Wu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19767-19788, 2023.

Abstract

In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In this paper, we revisit the weighted aggregation process and gain new insights into the training dynamics of FL. First, we find that the sum of weights can be smaller than 1, causing global weight shrinking effect (analogous to weight decay) and improving generalization. We explore how the optimal shrinking factor is affected by clients’ data heterogeneity and local epochs. Second, we dive into the relative aggregation weights among clients to depict the clients’ importance. We develop client coherence to study the learning dynamics and find a critical point that exists. Before entering the critical point, more coherent clients play more essential roles in generalization. Based on the above insights, we propose an effective method for Federated Learning with Learnable Aggregation Weights, named as FedLAW. Extensive experiments verify that our method can improve the generalization of the global model by a large margin on different datasets and models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-li23s, title = {Revisiting Weighted Aggregation in Federated Learning with Neural Networks}, author = {Li, Zexi and Lin, Tao and Shang, Xinyi and Wu, Chao}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {19767--19788}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/li23s/li23s.pdf}, url = {https://proceedings.mlr.press/v202/li23s.html}, abstract = {In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In this paper, we revisit the weighted aggregation process and gain new insights into the training dynamics of FL. First, we find that the sum of weights can be smaller than 1, causing global weight shrinking effect (analogous to weight decay) and improving generalization. We explore how the optimal shrinking factor is affected by clients’ data heterogeneity and local epochs. Second, we dive into the relative aggregation weights among clients to depict the clients’ importance. We develop client coherence to study the learning dynamics and find a critical point that exists. Before entering the critical point, more coherent clients play more essential roles in generalization. Based on the above insights, we propose an effective method for Federated Learning with Learnable Aggregation Weights, named as FedLAW. Extensive experiments verify that our method can improve the generalization of the global model by a large margin on different datasets and models.} }
Endnote
%0 Conference Paper %T Revisiting Weighted Aggregation in Federated Learning with Neural Networks %A Zexi Li %A Tao Lin %A Xinyi Shang %A Chao Wu %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-li23s %I PMLR %P 19767--19788 %U https://proceedings.mlr.press/v202/li23s.html %V 202 %X In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In this paper, we revisit the weighted aggregation process and gain new insights into the training dynamics of FL. First, we find that the sum of weights can be smaller than 1, causing global weight shrinking effect (analogous to weight decay) and improving generalization. We explore how the optimal shrinking factor is affected by clients’ data heterogeneity and local epochs. Second, we dive into the relative aggregation weights among clients to depict the clients’ importance. We develop client coherence to study the learning dynamics and find a critical point that exists. Before entering the critical point, more coherent clients play more essential roles in generalization. Based on the above insights, we propose an effective method for Federated Learning with Learnable Aggregation Weights, named as FedLAW. Extensive experiments verify that our method can improve the generalization of the global model by a large margin on different datasets and models.
APA
Li, Z., Lin, T., Shang, X. & Wu, C.. (2023). Revisiting Weighted Aggregation in Federated Learning with Neural Networks. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:19767-19788 Available from https://proceedings.mlr.press/v202/li23s.html.

Related Material