← Back to all news
arXiv Machine Learning By Zihan Zhang, Leon Wong, Blesson Varghese

Ampere: Communication-Efficient and High-Accuracy Split Federated Learning

Read the original on arXiv Machine Learning →

Ampere is a new split federated learning system that reduces both on‑device computation and device‑server communication while improving accuracy. It trains device and server blocks sequentially with local losses, eliminating gradient transfers, and uses a lightweight auxiliary network to consolidate activations into a single transfer. Experiments on CNNs and Transformers show up to 11.70 pp accuracy gains, 18.6× faster training, 911× less communication, and 14.5× less computation compared to state‑of‑the‑art SFL baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 3

FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices

FedSAP is a federated learning framework that addresses heterogeneous edge devices by using structured pruning as a budget-constrained tri-state channel allocation. It partitions model channels into a Global pool, pseudo-domain-specific Private pools, and a Dropped state, allowing broadly useful features to be shared while isolating domain-sensitive updates. Experiments on Digits and Office-Caltech datasets show FedSAP achieving higher mean global accuracy than the strongest baseline while supporting up to 80% client pruning ratios.

By Wentao Yue, Tianyou Lai, Hongji Li, Qingyu Mao, Qilei Li
efficiency
More like this →
arXiv Machine Learning
Oct 3

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

The paper introduces Local Superior Soups, a model‑interpolation based local training technique designed to improve the adaptation of large pre‑trained models in cross‑silo federated learning. By encouraging exploration of a connected low‑loss basin through regularized interpolation, the method reduces the number of communication rounds needed and boosts performance across several widely used FL datasets. The authors provide code for reproducibility.

By Minghui Chen, Meirui Jiang, Xin Zhang, Qi Dou, Zehua Wang, Xiaoxiao Li
More like this →