Papers › FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
Junyu Luo, Jianlei Yang, Xucheng Ye, Xin Guo, Weisheng Zhao
Federated learning aims to protect users' privacy while performing data analysis from different participants. However, it is challenging to guarantee the training efficiency on heterogeneous systems due to the various computational capabilities and communication bottlenecks. In this work, we propose FedSkel to enable computation-efficient and communication-efficient federated learning on edge devices by only updating the model's essential parts, named skeleton networks. FedSkel is evaluated on real edge devices with imbalanced datasets. Experimental results show that it could achieve up to 5.52× speedups for CONV layers' back-propagation, 1.82× speedups for the whole training process, and reduce 64.8% communication cost, with negligible accuracy loss.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections