Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation
This addresses the challenge of learning personalized models for clients with imbalanced data in privacy-preserving federated settings, representing an incremental advance in handling specific data distribution issues.
The paper tackles the joint problem of data heterogeneity and long-tail distribution in personalized federated learning, proposing FedAFA which uses adversarial feature augmentation to enhance minority classes, resulting in significant performance improvements over state-of-the-art methods.
Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods generally assume that the underlying global data across all clients are uniformly distributed without considering the long-tail distribution. The joint problem of data heterogeneity and long-tail distribution in the FL environment is more challenging and severely affects the performance of personalized models. In this paper, we propose a PFL method called Federated Learning with Adversarial Feature Augmentation (FedAFA) to address this joint problem in PFL. FedAFA optimizes the personalized model for each client by producing a balanced feature set to enhance the local minority classes. The local minority class features are generated by transferring the knowledge from the local majority class features extracted by the global model in an adversarial example learning manner. The experimental results on benchmarks under different settings of data heterogeneity and long-tail distribution demonstrate that FedAFA significantly improves the personalized performance of each client compared with the state-of-the-art PFL algorithm. The code is available at https://github.com/pxqian/FedAFA.