FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling

Dapeng Wu, Hong Huang, Jinhai Yang, Yuan Chen, Jiaxun Ye

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• Little0o0/FedRTS

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Federated Learning (FL) enables collaborative model training across distributed clients without data sharing, but its high computational and communication demands strain resource-constrained devices. While existing methods use dynamic pruning to improve efficiency by periodically adjusting sparse model topologies while maintaining sparsity, these approaches suffer from issues such as greedy adjustments, unstable topologies, and communication inefficiency, resulting in less robust models and suboptimal performance under data heterogeneity and partial client availability. To address these challenges, we propose Federated Robust pruning via combinatorial Thompson Sampling (FedRTS), a novel framework designed to develop robust sparse models. FedRTS enhances robustness and performance through its Thompson Sampling-based Adjustment (TSAdj) mechanism, which uses probabilistic decisions informed by stable and farsighted information, instead of deterministic decisions reliant on unstable and myopic information in previous methods. Extensive experiments demonstrate that FedRTS achieves state-of-the-art performance in computer vision and natural language processing tasks while reducing communication costs, particularly excelling in scenarios with heterogeneous data distributions and partial client participation. Our codes are available at: https://github.com/Little0o0/FedRTS. Preprint. Under review.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.19122")
get_code_for_paper("2501.19122")
have("2501.19122")

Connect an agent — have() is free.