paper-with-me

홈 › Papers

FedImpro: Measuring and Improving Client Update in Federated Learning

2024-02-10 · Zhenheng Tang, Yonggang Zhang, Shaohuai Shi, Xinmei Tian, Tongliang Liu, Bo Han, Xiaowen Chu

Federated Learning (FL) models often experience client drift caused by heterogeneous data, where the distribution of data differs across clients. To address this issue, advanced research primarily focuses on manipulating the existing gradients to achieve more consistent client models. In this paper, we present an alternative perspective on client drift and aim to mitigate it by generating improved local models. First, we analyze the generalization contribution of local training and conclude that this generalization contribution is bounded by the conditional Wasserstein distance between the data distribution of different clients. Then, we propose FedImpro, to construct similar conditional distributions for local training. Specifically, FedImpro decouples the model into high-level and low-level components, and trains the high-level portion on reconstructed feature distributions. This approach enhances the generalization contribution and reduces the dissimilarity of gradients in FL. Experimental results show that FedImpro can help FL defend against data heterogeneity and enhance the generalization performance of the model.

📄 PDF Abstract BibTeX arXiv:2402.07011

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

LoMar: A Local Defense Against Poisoning Attack on Federated Learning

2022-01-08 · Xingyu Li, Zhe Qu, Shangqing Zhao, Bo Tang 외

Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network. Though FL enables a privacy-preserving mobile edge c…

Density EstimationEdge-computingFederated LearningPrivacy Preserving

Optimal Client Sampling for Federated Learning

2020-10-26 · NeurIPS 2021 12 · Wenlin Chen, Samuel Horvath, Peter Richtarik

It is well understood that client-master communication can be a primary bottleneck in Federated Learning. In this work, we address this issue with a novel client subsampling scheme, where we restrict the number of client…

Federated Learning

Semi-Decentralized Federated Learning with Collaborative Relaying

2022-05-23 · Michal Yemini, Rajarshi Saha, Emre Ozfatura, Deniz Gündüz 외

We present a semi-decentralized federated learning algorithm wherein clients collaborate by relaying their neighbors' local updates to a central parameter server (PS). At every communication round to the PS, each client …

Federated Learning

A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

2020-04-22 · Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow 외

Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients (edge devices). FL offers default client privacy by allowing clients to keep their …

Federated Learning

Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA

2026-05-07 · Jinqian Chen, Chang Liu, Jihua Zhu arxiv

Federated LoRA enables parameter-efficient adaptation of large language models under decentralized data and limited client resources.However, directly averaging LoRA factors is representation-dependent: the same intrinsi…