Robust Training of Federated Models with Extremely Label Deficiency

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yonggang, Yang, Zhiqin, Tian, Xinmei, Wang, Nannan, Liu, Tongliang, Han, Bo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910340492558336
author Zhang, Yonggang
Yang, Zhiqin
Tian, Xinmei
Wang, Nannan
Liu, Tongliang
Han, Bo
author_facet Zhang, Yonggang
Yang, Zhiqin
Tian, Xinmei
Wang, Nannan
Liu, Tongliang
Han, Bo
contents Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency. Advanced FSSL methods predominantly focus on training a single model on each client. However, this approach could lead to a discrepancy between the objective functions of labeled and unlabeled data, resulting in gradient conflicts. To alleviate gradient conflict, we propose a novel twin-model paradigm, called Twin-sight, designed to enhance mutual guidance by providing insights from different perspectives of labeled and unlabeled data. In particular, Twin-sight concurrently trains a supervised model with a supervised objective function while training an unsupervised model using an unsupervised objective function. To enhance the synergy between these two models, Twin-sight introduces a neighbourhood-preserving constraint, which encourages the preservation of the neighbourhood relationship among data features extracted by both models. Our comprehensive experiments on four benchmark datasets provide substantial evidence that Twin-sight can significantly outperform state-of-the-art methods across various experimental settings, demonstrating the efficacy of the proposed Twin-sight.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Training of Federated Models with Extremely Label Deficiency
Zhang, Yonggang
Yang, Zhiqin
Tian, Xinmei
Wang, Nannan
Liu, Tongliang
Han, Bo
Machine Learning
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency. Advanced FSSL methods predominantly focus on training a single model on each client. However, this approach could lead to a discrepancy between the objective functions of labeled and unlabeled data, resulting in gradient conflicts. To alleviate gradient conflict, we propose a novel twin-model paradigm, called Twin-sight, designed to enhance mutual guidance by providing insights from different perspectives of labeled and unlabeled data. In particular, Twin-sight concurrently trains a supervised model with a supervised objective function while training an unsupervised model using an unsupervised objective function. To enhance the synergy between these two models, Twin-sight introduces a neighbourhood-preserving constraint, which encourages the preservation of the neighbourhood relationship among data features extracted by both models. Our comprehensive experiments on four benchmark datasets provide substantial evidence that Twin-sight can significantly outperform state-of-the-art methods across various experimental settings, demonstrating the efficacy of the proposed Twin-sight.
title Robust Training of Federated Models with Extremely Label Deficiency
topic Machine Learning
url https://arxiv.org/abs/2402.14430