FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
This addresses the privacy-performance trade-off in federated learning for distributed clients, but it appears incremental as it builds on existing feature-sharing ideas.
The paper tackles data heterogeneity in federated learning by proposing FedFed, which partitions data into performance-sensitive and performance-robust features, sharing the former globally to improve model performance while preserving privacy, with experiments showing efficacy in promoting performance.
Federated learning (FL) typically faces data heterogeneity, i.e., distribution shifting among clients. Sharing clients' information has shown great potentiality in mitigating data heterogeneity, yet incurs a dilemma in preserving privacy and promoting model performance. To alleviate the dilemma, we raise a fundamental question: \textit{Is it possible to share partial features in the data to tackle data heterogeneity?} In this work, we give an affirmative answer to this question by proposing a novel approach called {\textbf{Fed}erated \textbf{Fe}ature \textbf{d}istillation} (FedFed). Specifically, FedFed partitions data into performance-sensitive features (i.e., greatly contributing to model performance) and performance-robust features (i.e., limitedly contributing to model performance). The performance-sensitive features are globally shared to mitigate data heterogeneity, while the performance-robust features are kept locally. FedFed enables clients to train models over local and shared data. Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.