Exploring Vacant Classes in Label-Skewed Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Kuangpu, Ding, Yuhe, Liang, Jian, He, Ran, Wang, Zilei, Tan, Tieniu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917869276626944
author Guo, Kuangpu
Ding, Yuhe
Liang, Jian
He, Ran
Wang, Zilei
Tan, Tieniu
author_facet Guo, Kuangpu
Ding, Yuhe
Liang, Jian
He, Ran
Wang, Zilei
Tan, Tieniu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02329
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Vacant Classes in Label-Skewed Federated Learning
Guo, Kuangpu
Ding, Yuhe
Liang, Jian
He, Ran
Wang, Zilei
Tan, Tieniu
Machine Learning
Computer Vision and Pattern Recognition
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.
title Exploring Vacant Classes in Label-Skewed Federated Learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.02329