arXiv Machine Learning August 31, 2026 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.

arXiv Machine Learning

Aug 5

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

arXiv:2608. 03324v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy.

By Shengyang Li, Yiting Dong, Liuyang Song, Ximing Wang, Luyuan Xie, Cong Li, Qingni Shen, Zhaofei Yu

efficiency benchmarks safety

arXiv AI

Jun 10

QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning

arXiv:2606. 09869v1 Announce Type: cross Abstract: Federated Learning (FL) combined with Split Learning (SL) is a privacy preserving paradigm that enables training deep neural networks (DNNs) on resource constrained devices while reducing overall training cost.

By Nazmus Shakib Shadin, Xinyue Zhang, Jingyi Wang, Miao Pan

reinforcement-learning safety

arXiv AI

Aug 11

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

arXiv:2608. 09208v1 Announce Type: cross Abstract: Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL).

By Van Truong Vo, Khoa Nguyen, Taehong Kim

Hugging Face Trending Papers

Aug 10

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). However, DFL suffers from convergence inefficiency under data heterogeneity due to the use of a uniform learning rate (LR) that ignores layer-specific optimization needs.

arXiv AI

Aug 18

FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

arXiv:2608. 14654v1 Announce Type: cross Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy.

By Hai Anh Tran, Cuong Ta, Truong X. Tran

safety

arXiv Machine Learning

Jun 9

Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design

arXiv:2410. 05662v4 Announce Type: replace Abstract: Most federated learning (FL) approaches assume a fixed device set.

By Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton

One email a morning, machine-written

Related stories

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design