Papers › SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients...

SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning

29 Nov 2021arXiv:2111.14345archive 2025-07-28

Sixing Yu, Phuong Nguyen, Waqwoya Abebe, Wei Qian, Ali Anwar, Ali Jannesari

Federated learning~(FL) facilitates the training and deploying AI models on edge devices. Preserving user data privacy in FL introduces several challenges, including expensive communication costs, limited resources, and data heterogeneity. In this paper, we propose SPATL, an FL method that addresses these issues by: (a) introducing a salient parameter selection agent and communicating selected parameters only; (b) splitting a model into a shared encoder and a local predictor, and transferring its knowledge to heterogeneous clients via the locally customized predictor. Additionally, we leverage a gradient control mechanism to further speed up model convergence and increase robustness of training processes. Experiments demonstrate that SPATL reduces communication overhead, accelerates model inference, and enables stable training processes with better results compared to state-of-the-art methods. Our approach reduces communication cost by up to 86.45%, accelerates local inference by reducing up to 39.7% FLOPs on VGG-11, and requires 7.4 × less communication overhead when training ResNet-20.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yusx-swapp/spatl officialmentioned in paperpytorch report

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

Federated LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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