FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
This addresses efficiency and robustness issues in Federated Learning for resource-constrained devices, representing an incremental improvement over existing dynamic pruning methods.
The paper tackles the problem of high computational and communication demands in Federated Learning by proposing FedRTS, a framework that uses combinatorial Thompson Sampling for robust pruning, achieving state-of-the-art performance in vision and NLP tasks while reducing communication costs, especially under data heterogeneity and partial client availability.
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, 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