FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
This addresses data heterogeneity issues in federated learning for privacy-preserving AI applications, representing an incremental improvement over existing proximal methods.
The paper tackles performance degradation in federated learning due to heterogeneous client data by proposing FedSOL, a method that uses orthogonal learning to balance local and global objectives, achieving state-of-the-art results in experiments.
Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy, it often suffers from significant performance degradation when clients have heterogeneous data distributions. This data heterogeneity causes the model to forget the global knowledge acquired from previously sampled clients after being trained on local datasets. Although the introduction of proximal objectives in local updates helps to preserve global knowledge, it can also hinder local learning by interfering with local objectives. To address this problem, we propose a novel method, Federated Stabilized Orthogonal Learning (FedSOL), which adopts an orthogonal learning strategy to balance the two conflicting objectives. FedSOL is designed to identify gradients of local objectives that are inherently orthogonal to directions affecting the proximal objective. Specifically, FedSOL targets parameter regions where learning on the local objective is minimally influenced by proximal weight perturbations. Our experiments demonstrate that FedSOL consistently achieves state-of-the-art performance across various scenarios.