paper-with-me

홈 › Papers

Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning

2025-01-01 · CVPR 2025 1 · Xiangtao Zhang, Sheng Li, Ao Li, Yipeng Liu, Fan Zhang, Ce Zhu, Le Zhang

Heterogeneous Federated Learning (HFL) has received widespread attention due to its adaptability to different models and data. The HFL approach utilizing auxiliary models for knowledge transfer enhances flexibility. However, existing frameworks face the challenges of aggregation bias and local overfitting. To address these issues, we propose FedSCE. It reduces the degree of freedom of update and improves generalization performance by limiting the specific layer of local model update to the local subspace. The subspace is dynamically updated to ensure coverage of the latest model update trajectory. Additionally, FedSCE evaluates client contributions based on the update distance of the auxiliary model in feature space and parameter space, achieving adaptive weighted aggregation. We validate our approach in both feature-skewed and label-skewed scenarios, demonstrating that on Office10, our method exceeds the best baseline by 3.87%. The code will be available at https://github.com/AVC2-UESTC/FedSCE.git.

📄 PDF Abstract BibTeX

Code (1)

avc2-uestc/fedsce 공식 구현

Tasks

Federated LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning

2026-05-19 · T. Tony Cai, Yicheng Li arxiv

Federated differentially private protocols can communicate over many adaptive rounds and reuse each client's local samples. Existing lower bound arguments for federated DP are often restricted to noninteractive protocols…

Federated Learning

Subspace-Constrained Federated Learning with Low-Rank Adaptation

2026-06-21 · Neranjan Senarath, Rohit Muralitharan, Sadia Asif arxiv

Federated low-rank adaptation methods are attractive for fine-tuning large models under communication and privacy constraints, but heterogeneous client data can induce geometric misalignment between local low-rank update…

Federated Learning

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

2023-11-03 · Aditya Desai, Benjamin Meisburger, Zichang Liu, Anshumali Shrivastava

Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models are trained on a central server. However,…

Collaborative FilteringFederated LearningRecommendation Systems

CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks

2025-10-23 · Ke Xing, Yanjie Dong, Xiaoyi Fan, Runhao Zeng 외 arxiv

Personalized federated learning (PFL) addresses a critical challenge of collaboratively training customized models for clients with heterogeneous and scarce local data. Conventional federated learning, which relies on a …

Personalized Federated Learning

An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data

2025-09-05 · Jiaojiao Zhang, Yuqi Xu, Kun Yuan arxiv

This work addresses the key challenges of applying federated learning to large-scale deep neural networks, particularly the issue of client drift due to data heterogeneity across clients and the high costs of communicati…

Federated Learning