FedALA: Adaptive Local Aggregation for Personalized Federated Learning
This addresses the problem of poor generalization in federated learning for clients with heterogeneous data, offering an incremental improvement over existing personalized FL methods.
The paper tackles the challenge of statistical heterogeneity in federated learning by proposing FedALA, an adaptive local aggregation method for personalized federated learning, which improves test accuracy by up to 3.27% over baselines and up to 24.19% when applied to other methods.
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. The key component of FedALA is an Adaptive Local Aggregation (ALA) module, which can adaptively aggregate the downloaded global model and local model towards the local objective on each client to initialize the local model before training in each iteration. To evaluate the effectiveness of FedALA, we conduct extensive experiments with five benchmark datasets in computer vision and natural language processing domains. FedALA outperforms eleven state-of-the-art baselines by up to 3.27% in test accuracy. Furthermore, we also apply ALA module to other federated learning methods and achieve up to 24.19% improvement in test accuracy.