← Back to all news
arXiv Machine Learning By Xinghao Wu, Xuefeng Liu, Jianwei Niu, Guogang Zhu, Mingjia Shi, Shaojie Tang, Jing Yuan

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

Read the original on arXiv Machine Learning →

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.

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
Aug 18

Global Federated Learning Strategies for Building Efficient Personalized Models

arXiv:2608. 15107v1 Announce Type: new Abstract: Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously.

By Seongyoon Kim
reinforcement-learningfine-tuningefficiencysafety
More like this →
arXiv Machine Learning
Aug 31

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

By Yiming Xie, Lili Su, Ningfang Mi
fine-tuning
More like this →