arXiv Machine Learning August 31, 2026 By Yiming Xie, Lili Su, Ningfang Mi

Beyond Non-IID: Learner--Client Distribution Mismatch in Federated Learning

Read the original on arXiv Machine Learning →

The paper addresses the mismatch between learner and client data distributions in federated learning, noting that traditional client selection methods often ignore this misalignment. It introduces a dynamic, influence-aware client selection framework that uses a small proxy dataset to estimate each client's utility for the learner’s objective, prioritizing informative sources while mitigating noise and heterogeneity. Experiments on CIFAR-10 with heterogeneous partitions show the proposed method outperforms static and dynamic baselines, achieving faster convergence and higher accuracy.

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.

fine-tuning

arXiv AI

Aug 18

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

arXiv:2608. 15639v1 Announce Type: cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients.

By Wenhao Yuan, Chenchen Lin, Wenhao Hu, Jian Chen, Jinfeng Xu, Shujie Li, Edith Cheuk Han Ngai

benchmarks safety

arXiv Machine Learning

Aug 13

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

arXiv:2608. 12108v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed clients while keeping data local.

By Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay

Hugging Face Trending Papers

Aug 16

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

\textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split stra...

benchmarks safety

arXiv Machine Learning

Aug 4

CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning

arXiv:2608. 02222v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering significant advantages in communication efficiency and privacy preservation.

By Zijian Jiang, Chaoli Sun, Handing Wang, Xilu Wang

efficiency benchmarks safety

arXiv AI

Jun 30

Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning

arXiv:2606. 28835v1 Announce Type: cross Abstract: Federated Learning (FL) emerged as a promising distributed machine learning paradigm.

By Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu, Zewei Liu, Edith Cheuk Han Ngai

benchmarks

arXiv Machine Learning

3d ago

Federated Personalization of Early-Exit Networks

arXiv:2601.10015v2 Announce Type: replace Abstract: Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneou...

By Boyi Liu, Zimu Zhou, Cheng Fang, Yongxin Tong

efficiency benchmarks

One email a morning, machine-written

Related stories

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning

Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning

Federated Personalization of Early-Exit Networks