Aggregation Weighting of Federated Learning via Generalization Bound Estimation
This work addresses performance issues in Federated Learning for distributed data scenarios, but it is incremental as it builds on existing FL algorithms with a novel weighting method.
The paper tackles the problem of unfairness and performance degradation in Federated Learning due to naive weighting based on sample proportions, by proposing a new aggregation strategy that uses generalization bound estimation, which significantly improves performance on benchmark datasets.
Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions. However, this naive weighting method may lead to unfairness and degradation in model performance due to statistical heterogeneity and the inclusion of noisy data among clients. Theoretically, distributional robustness analysis has shown that the generalization performance of a learning model with respect to any shifted distribution is bounded. This motivates us to reconsider the weighting approach in federated learning. In this paper, we replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model. Specifically, we estimate the upper and lower bounds of the second-order origin moment of the shifted distribution for the current local model, and then use these bounds disagreements as the aggregation proportions for weightings in each communication round. Experiments demonstrate that the proposed weighting strategy significantly improves the performance of several representative FL algorithms on benchmark datasets.