paper-with-me

홈 › Papers

Exploring Vacant Classes in Label-Skewed Federated Learning

2024-01-04 · Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan

Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compared to the global model. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates both vacant-class distillation and logit suppression simultaneously. Specifically, vacant-class distillation leverages knowledge distillation during local training on each client to retain essential information related to vacant classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods across diverse datasets with varying degrees of label skews. Our code is available at https://github.com/krumpguo/FedVLS.

📄 PDF Abstract BibTeX arXiv:2401.02329

Code (1)

krumpguo/fedvls 공식 구현 pytorch

Tasks

Federated LearningKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

CalFAT: Calibrated Federated Adversarial Training with Label Skewness

2022-05-30 · Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu

Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks. To improve the adversarial robustness of FL, federated adversarial training (FAT) meth…

Adversarial RobustnessFederated Learning

Federated Unlearning Model Recovery in Data with Skewed Label Distributions

2024-12-18 · Xinrui Yu, Wenbin Pei, Bing Xue, Qiang Zhang

In federated learning, federated unlearning is a technique that provides clients with a rollback mechanism that allows them to withdraw their data contribution without training from scratch. However, existing research ha…

DenoisingFederated Learning

Understanding the Role of Layer Normalization in Label-Skewed Federated Learning

2023-08-18 · Guojun Zhang, Mahdi Beitollahi, Alex Bie, Xi Chen

Layer normalization (LN) is a widely adopted deep learning technique especially in the era of foundation models. Recently, LN has been shown to be surprisingly effective in federated learning (FL) with non-i.i.d. data. H…

Federated Learning

Federated Learning with Label Distribution Skew via Logits Calibration

2022-09-01 · Jie Zhang, Zhiqi Li, Bo Li, Jianghe Xu 외

Traditional federated optimization methods perform poorly with heterogeneous data (ie, accuracy reduction), especially for highly skewed data. In this paper, we investigate the label distribution skew in FL, where the di…

Federated Learning

Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization

2024-08-15 · Shunxin Guo, Hongsong Wang, Shuxia Lin, Zhiqiang Kou 외

Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significant challenge of federated learning is da…

Federated Learning