paper-with-me

Papers

Rethinking Client Drift in Federated Learning: A Logit Perspective

2023-08-20 · Yunlu Yan, Chun-Mei Feng, Mang Ye, WangMeng Zuo, Ping Li, Rick Siow Mong Goh, Lei Zhu, C. L. Philip Chen

Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. However, the real-world non-IID data will lead to client drift which degrades the performance of FL. Interestingly, we find that the difference in logits between the local and global models increases as the model is continuously updated, thus seriously deteriorating FL performance. This is mainly due to catastrophic forgetting caused by data heterogeneity between clients. To alleviate this problem, we propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models. FedCSD does not simply transfer global knowledge to local clients, as an undertrained global model cannot provide reliable knowledge, i.e., class similarity information, and its wrong soft labels will mislead the optimization of local models. Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype. To enhance the quality of global logits, FedCSD adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them to mislead local optimization. Extensive experiments demonstrate the superiority of our method over the state-of-the-art federated learning approaches in various heterogeneous settings. The source code will be released.

📄 PDF Abstract BibTeX arXiv:2308.10162

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Drift-Aware Federated Learning: A Causal Perspective

2025-03-12 · Yunjie Fang, Sheng Wu, Tao Yang, Xiaofeng Wu 외

Federated learning (FL) facilitates collaborative model training among multiple clients while preserving data privacy, often resulting in enhanced performance compared to models trained by individual clients. However, fa…

Federated Learning

Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment

2026-02-02 · Hongyi Peng, Han Yu, Xiaoxiao Li, Qiang Yang arxiv

Low-Rank Adaptation (LoRA) is widely used for federated fine-tuning. Yet under non-IID settings, it can substantially underperform full-parameter fine-tuning. Through with-high-probability robustness analysis, we uncover…

Federated Learning

FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning

2026-02-15 · Hamza Reguieg, Mohamed El Kamili, Essaid Sabir arxiv

Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and…

Knowledge DistillationFederated Learning

FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering

2026-07-05 · Liyang Yuan, Yibo Yang, Dandan Guo arxiv

Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centraliz…

Federated Learning

OvA-LP: A Simple and Efficient Framework for Federated Learning on Non-IID Data

2025-11-07 · Dongjin Park, Hasung Yeo, Joon-Woo Lee arxiv

Federated fine-tuning (FFT) adapts foundation models to decentralized data but remains fragile under heterogeneous client distributions due to local drift, i.e., client-level update divergences that induce systematic bia…

Federated Learning