paper-with-me

홈 › Papers

Tackling the Non-IID Issue in Heterogeneous Federated Learning by Gradient Harmonization

2023-09-13 · Xinyu Zhang, Weiyu Sun, Ying Chen

Federated learning (FL) is a privacy-preserving paradigm for collaboratively training a global model from decentralized clients. However, the performance of FL is hindered by non-independent and identically distributed (non-IID) data and device heterogeneity. In this work, we revisit this key challenge through the lens of gradient conflicts on the server side. Specifically, we first investigate the gradient conflict phenomenon among multiple clients and reveal that stronger heterogeneity leads to more severe gradient conflicts. To tackle this issue, we propose FedGH, a simple yet effective method that mitigates local drifts through Gradient Harmonization. This technique projects one gradient vector onto the orthogonal plane of the other within conflicting client pairs. Extensive experiments demonstrate that FedGH consistently enhances multiple state-of-the-art FL baselines across diverse benchmarks and non-IID scenarios. Notably, FedGH yields more significant improvements in scenarios with stronger heterogeneity. As a plug-and-play module, FedGH can be seamlessly integrated into any FL framework without requiring hyperparameter tuning.

📄 PDF Abstract BibTeX arXiv:2309.06692

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

Federated Learning with Projected Trajectory Regularization

2023-12-22 · Tiejin Chen, Yuanpu Cao, Yujia Wang, Cho-Jui Hsieh 외

Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across…

Federated Learning

PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets

2026-05-22 · Anisa Halimi, Liubov Nedoshivina, Kieran Fraser, Stefano Braghin arxiv

The growing availability of clinical data has increased the use of machine learning, yet centralized data aggregation is often infeasible for sensitive health information. Federated Learning (FL) offers a distributed alt…

Federated Learning

Federated Learning based on Pruning and Recovery

2024-03-16 · Chengjie Ma

A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning …

Federated Learning

Automated Metadata Harmonization Using Entity Resolution & Contextual Embedding

2020-10-17 · Kunal Sawarkar, Meenkakshi Kodati

ML Data Curation process typically consist of heterogeneous & federated source systems with varied schema structures; requiring curation process to standardize metadata from different schemas to an inter-operable schema.…

Entity Resolution

No One Left Behind: Real-World Federated Class-Incremental Learning

2023-02-02 · Jiahua Dong, Hongliu Li, Yang Cong, Gan Sun 외

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known an…

class-incremental learningClass Incremental LearningFederated LearningIncremental Learning