paper-with-me

홈 › Papers

Neural Collapse Inspired Federated Learning with Non-iid Data

2023-03-27 · Chenxi Huang, Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server. Although many studies have been proposed to address this challenge, they only focus on local training and aggregation processes to smooth the changes and fail to achieve high performance with deep learning models. Inspired by the phenomenon of neural collapse, we force each client to be optimized toward an optimal global structure for classification. Specifically, we initialize it as a random simplex Equiangular Tight Frame (ETF) and fix it as the unit optimization target of all clients during the local updating. After guaranteeing all clients are learning to converge to the global optimum, we propose to add a global memory vector for each category to remedy the parameter fluctuation caused by the bias of the intra-class condition distribution among clients. Our experimental results show that our method can improve the performance with faster convergence speed on different-size datasets.

📄 PDF Abstract BibTeX arXiv:2303.16066

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

fail 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems

2025-06-24 · Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li

Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments c…

Federated Learning

You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data

2025-03-10 · Shanshan Yan, Zexi Li, Chao Wu, Meng Pang 외

Data heterogeneity, stemming from local non-IID data and global long-tailed distributions, is a major challenge in federated learning (FL), leading to significant performance gaps compared to centralized learning. Previo…

Federated LearningRepresentation Learning

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

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

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

2024-01-17 · Zikai Xiao, Zihan Chen, Liyinglan Liu, Yang Feng 외

Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution, has garnered considerable attention in recent times. In…

Federated LearningPersonalized Federated LearningRepresentation Learning