Tag
This paper proposes FedSLM, a parameter-centric framework for federated fine-tuning of foundation models with heterogeneous compressed clients, using SVD-based decomposition and a weak-to-strong elicitation step to handle resource asymmetry. Experiments show it outperforms existing federated baselines while reducing client GPU memory by ~50%.
The paper introduces MESH-FL, an entropy-guided matrix product state compression framework for multimodal federated learning on edge devices. It adaptively allocates compression ranks per layer and modality, achieving up to 56.8× compression and 2.01% final accuracy improvement over uncompressed FedAvg on a heterogeneous Raspberry Pi cluster.