Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
This addresses system heterogeneity in federated learning for distributed systems, but it is incremental as it builds on existing homogeneous methods.
The paper tackles the challenge of system heterogeneity in federated learning by proposing InCo Aggregation, which uses internal cross-layer gradients to extend the capabilities of homogeneous methods like FedAvg to handle heterogeneity, with experimental results validating its effectiveness.
Federated learning (FL) inevitably confronts the challenge of system heterogeneity in practical scenarios. To enhance the capabilities of most model-homogeneous FL methods in handling system heterogeneity, we propose a training scheme that can extend their capabilities to cope with this challenge. In this paper, we commence our study with a detailed exploration of homogeneous and heterogeneous FL settings and discover three key observations: (1) a positive correlation between client performance and layer similarities, (2) higher similarities in the shallow layers in contrast to the deep layers, and (3) the smoother gradients distributions indicate the higher layer similarities. Building upon these observations, we propose InCo Aggregation that leverages internal cross-layer gradients, a mixture of gradients from shallow and deep layers within a server model, to augment the similarity in the deep layers without requiring additional communication between clients. Furthermore, our methods can be tailored to accommodate model-homogeneous FL methods such as FedAvg, FedProx, FedNova, Scaffold, and MOON, to expand their capabilities to handle the system heterogeneity. Copious experimental results validate the effectiveness of InCo Aggregation, spotlighting internal cross-layer gradients as a promising avenue to enhance the performance in heterogeneous FL.