paper-with-me

Papers

Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

2022-10-01 · Yujun Shi, Jian Liang, Wenqing Zhang, Vincent Y. F. Tan, Song Bai

Federated learning aims to train models collaboratively across different clients without the sharing of data for privacy considerations. However, one major challenge for this learning paradigm is the {\em data heterogeneity} problem, which refers to the discrepancies between the local data distributions among various clients. To tackle this problem, we first study how data heterogeneity affects the representations of the globally aggregated models. Interestingly, we find that heterogeneous data results in the global model suffering from severe {\em dimensional collapse}, in which representations tend to reside in a lower-dimensional space instead of the ambient space. Moreover, we observe a similar phenomenon on models locally trained on each client and deduce that the dimensional collapse on the global model is inherited from local models. In addition, we theoretically analyze the gradient flow dynamics to shed light on how data heterogeneity result in dimensional collapse for local models. To remedy this problem caused by the data heterogeneity, we propose {\sc FedDecorr}, a novel method that can effectively mitigate dimensional collapse in federated learning. Specifically, {\sc FedDecorr} applies a regularization term during local training that encourages different dimensions of representations to be uncorrelated. {\sc FedDecorr}, which is implementation-friendly and computationally-efficient, yields consistent improvements over baselines on standard benchmark datasets. Code: https://github.com/bytedance/FedDecorr.

📄 PDF Abstract BibTeX arXiv:2210.00226

Code (2)

Yujun-Shi/FedCLS 공식 구현 pytorch
bytedance/feddecorr 공식 구현 pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew

2025-09-16 · Can Peng, Yuyuan Liu, Yingyu Yang, Pramit Saha 외 arxiv

Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but remains challenging when client data are highly heterogeneous. These challenges are further ampli…

Federated Learning

CCFC++: Enhancing Federated Clustering through Feature Decorrelation

2024-02-20 · Jie Yan, Jing Liu, Yi-Zi Ning, Zhong-Yuan Zhang

In federated clustering, multiple data-holding clients collaboratively group data without exchanging raw data. This field has seen notable advancements through its marriage with contrastive learning, exemplified by Clust…

ClusteringContrastive Learning

Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity

2026-02-13 · Fei Wu, Jia Hu, Geyong Min, Shiqiang Wang arxiv

Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning scenarios, client heterogeneit…

Federated Learning

Stabilized Fine-Tuning with LoRA in Federated Learning: Mitigating the Side Effect of Client Size and Rank via the Scaling Factor

2026-03-09 · Jiayu Huang, Xiaohu Wu, Tiantian He, Qicheng Lao arxiv

Large Language Models (LLMs) are pivotal in natural language processing. The impracticality of full fine-tuning has prompted Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA), optimizing low-…

parameter-efficient fine-tuningFederated Learning

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

2023-03-17 · ICCV 2023 1 · Zexi Li, Xinyi Shang, Rui He, Tao Lin 외

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have use…

Classifier calibrationFederated Learning