Local Gradient Regulation Stabilizes Federated Learning under Client Heterogeneity

2026-01-07 · Ping Luo, Jiahuan Wang, Ziqing Wen, Tao Sun, Dongsheng Li arxiv

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its stability is fundamentally challenged by statistical heterogeneity in realistic deployments. Here, we show that client heterogeneity destabilizes FL primarily by distorting local gradient dynamics during client-side optimization, causing systematic drift that accumulates across communication rounds and impedes global convergence. This observation highlights local gradients as a key regulatory lever for stabilizing heterogeneous FL systems. Building on this insight, we develop a general client-side perspective that regulates local gradient contributions without incurring additional communication overhead. Inspired by swarm intelligence, we instantiate this perspective through Exploratory--Convergent Gradient Re-aggregation (ECGR), which balances well-aligned and misaligned gradient components to preserve informative updates while suppressing destabilizing effects. Theoretical analysis and extensive experiments, including evaluations on the LC25000 medical imaging dataset, demonstrate that regulating local gradient dynamics consistently stabilizes federated learning across state-of-the-art methods under heterogeneous data distributions.

📄 PDF Abstract BibTeX arXiv:2601.03584

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability

2025-12-19 · S M Ruhul Kabir Howlader, Xiao Chen, Yifei Xie, Lu Liu arxiv

Over the last few decades, machine learning (ML) and deep learning (DL) solutions have demonstrated their potential across many applications by leveraging large amounts of high-quality data. However, strict data-sharing …

Federated Learning

Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI

2026-08-21 · Shiva Shrestha, Kazi Shaharair Sharif, Zongxing Xie, Jiajing Huang 외 arxiv

Federated fine-tuning enables large language models to adapt on edge devices without centralizing private data, but practical deployments must address hardware instability and adversarial update corruption together. Ther…

FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards

2026-01-31 · Ziyao Wang, Daeun Jung, Yexiao He, Guoheng Sun 외 arxiv

Group Relative Policy Optimization (GRPO) has recently emerged as an effective approach for improving the reasoning capabilities of large language models through online multi-objective reinforcement learning. While perso…

Reinforcement Learning Mathematical Reasoning Federated Learning Code Generation

Federated Split BERT for Heterogeneous Text Classification

2022-05-26 · Zhengyang Li, Shijing Si, Jianzong Wang, Jing Xiao

Pre-trained BERT models have achieved impressive performance in many natural language processing (NLP) tasks. However, in many real-world situations, textual data are usually decentralized over many clients and unable to…

Classification Federated Learning Quantization text-classification+1

ADP-FL-MedSeg: Adaptive Differential Privacy for Federated Medical Segmentation Across Diverse Modalities

2026-04-07 · Puja Saha, Eranga Ukwatta arxiv

Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized set…

Medical Image Segmentation Brain Tumor Segmentation Skin Lesion Segmentation Federated Learning