Fed2: Feature-Aligned Federated Learning
This addresses the challenge of inefficient and misaligned model updates in federated learning for distributed data scenarios, representing an incremental advancement over existing methods.
The paper tackles the problem of structural feature misalignment in federated learning, which conventional methods like FedAvg ignore, by proposing Fed2, a feature-aligned framework that enhances convergence performance, achieving improvements in speed, accuracy, and efficiency under various data settings.
Federated learning learns from scattered data by fusing collaborative models from local nodes. However, the conventional coordinate-based model averaging by FedAvg ignored the random information encoded per parameter and may suffer from structural feature misalignment. In this work, we propose Fed2, a feature-aligned federated learning framework to resolve this issue by establishing a firm structure-feature alignment across the collaborative models. Fed2 is composed of two major designs: First, we design a feature-oriented model structure adaptation method to ensure explicit feature allocation in different neural network structures. Applying the structure adaptation to collaborative models, matchable structures with similar feature information can be initialized at the very early training stage. During the federated learning process, we then propose a feature paired averaging scheme to guarantee aligned feature distribution and maintain no feature fusion conflicts under either IID or non-IID scenarios. Eventually, Fed2 could effectively enhance the federated learning convergence performance under extensive homo- and heterogeneous settings, providing excellent convergence speed, accuracy, and computation/communication efficiency.