Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack
This addresses resource constraints and data heterogeneity in federated learning for edge computing, but it is incremental as it builds on existing personalized and sparse methods.
The paper tackles the challenge of data heterogeneity and limited client resources in federated learning by proposing FedCSPACK, a method that uses cosine sparsification and dual-weighted aggregation to reduce bandwidth and improve efficiency. Experiments on four datasets show it enhances communication and computational efficiency while maintaining high model accuracy.
Federated learning has drawn widespread interest from researchers, yet the data heterogeneity across edge clients remains a key challenge, often degrading model performance. Existing methods enhance model compatibility with data heterogeneity by splitting models and knowledge distillation. However, they neglect the insufficient communication bandwidth and computing power on the client, failing to strike an effective balance between addressing data heterogeneity and accommodating limited client resources. To tackle this limitation, we propose a personalized federated learning method based on cosine sparsification parameter packing and dual-weighted aggregation (FedCSPACK), which effectively leverages the limited client resources and reduces the impact of data heterogeneity on model performance. In FedCSPACK, the client packages model parameters and selects the most contributing parameter packages for sharing based on cosine similarity, effectively reducing bandwidth requirements. The client then generates a mask matrix anchored to the shared parameter package to improve the alignment and aggregation efficiency of sparse updates on the server. Furthermore, directional and distribution distance weights are embedded in the mask to implement a weighted-guided aggregation mechanism, enhancing the robustness and generalization performance of the global model. Extensive experiments across four datasets using ten state-of-the-art methods demonstrate that FedCSPACK effectively improves communication and computational efficiency while maintaining high model accuracy.