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.
By Yiming Xie, Lili Su, Ningfang Mi
The paper introduces FedPFT, a federated learning framework that tackles the feature‑classifier mismatch problem by using personalized prompts processed through a shared self‑attention transformation module. Unlike prior methods that either degrade the feature extractor or address the mismatch only after training, FedPFT aligns local features with the global classifier during training, improving aggregation and model performance. Experiments demonstrate that FedPFT surpasses state‑of‑the‑art methods by up to 5.07%, and gains up to 7.08% when combined with collaborative contrastive learning.
By Xinghao Wu, Xuefeng Liu, Jianwei Niu, Guogang Zhu, Mingjia Shi, Shaojie Tang, Jing Yuan
arXiv:2606. 13748v1 Announce Type: new Abstract: Personalized federated learning (PFL) is one of the important approaches in federated learning for addressing statistical heterogeneity while enabling client-specific adaptation.
By Kannanthodath Induchoodan Ajay Menon, Christian Prehofer, Yunfei Xu, Toru Hirano
Influence-Oriented Personalized Federated Learning (FedC^2I) introduces a framework that quantifies both client-level and class-level influence to enable adaptive parameter aggregation in federated learning. By modeling inter-client influence through influence vectors and matrices, FedC^2I allows clients to selectively acquire knowledge from similar peers and guides the aggregation of feature representations and classifiers. Experiments under non-IID settings show that FedC^2I outperforms existing federated learning methods in effectiveness, robustness, and interpretability.
By Yue Tan, Guodong Long, Jing Jiang, Chengqi Zhang
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
arXiv:2606. 14416v1 Announce Type: new Abstract: Federated learning (FL) often struggles with generalization due to heterogeneous client data.
By Dongwon Kim, Donghee Kim, Sung Kuk Shyn, Kwangsu Kim
arXiv:2405. 16472v2 Announce Type: replace Abstract: Contemporary AI faces the challenge of balancing generality with user-specific personalization.
By Shutong Chen, Guodong Long, Tianyi Zhou, Jie Ma, Jing Jiang, Chengqi Zhang
arXiv:2606. 15625v1 Announce Type: new Abstract: The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation.
By Yijun Lu, Zihan Fang, Pengpeng Qiao, Zheng Lin, Jing Yang, Yuxin Zhang, Por Lip Yee, Zhe Chen, Jun Luo
arXiv:2512. 24625v3 Announce Type: replace-cross Abstract: Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management.
By Zijian Zhao, Yitong Shang, Sen Li
arXiv:2512. 12737v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity.
By Li Xia
\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...
The paper introduces a latent information sharing scheme for federated learning that mitigates client drift by sharing a small amount of hidden‑layer activations. The authors demonstrate both theoretically and empirically that this approach improves training efficiency while maintaining convergence guarantees and data privacy. Compared to existing methods such as FedProx, SCAFFOLD, FedPVR, FedProto, and SplitFed, the proposed method achieves higher model accuracy within a fixed round budget without adding significant communication overhead.
By Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos, Baturalp Buyukates, Sunwoo Lee