Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zeng, Chusheng, Wang, Bocheng, Yuan, Jinghui, Wang, Rong, Chen, Mulin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929469304864768
author Zeng, Chusheng
Wang, Bocheng
Yuan, Jinghui
Wang, Rong
Chen, Mulin
author_facet Zeng, Chusheng
Wang, Bocheng
Yuan, Jinghui
Wang, Rong
Chen, Mulin
contents Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used to improve learning diversity, but commonly used random augmentation methods may destroy inherent semantics and cause noise; 2) the fixed positive and negative sample selection strategy is limited to deal with complex real data, thereby impeding the model's capability to capture fine-grained patterns and relationships. To reduce these problems, we propose the Clustering-guided Curriculum Graph contrastive Learning (CCGL) framework. CCGL uses clustering entropy as the guidance of the following graph augmentation and contrastive learning. Specifically, according to the clustering entropy, the intra-class edges and important features are emphasized in augmentation. Then, a multi-task curriculum learning scheme is proposed, which employs the clustering guidance to shift the focus from the discrimination task to the clustering task. In this way, the sample selection strategy of contrastive learning can be adjusted adaptively from early to late stage, which enhances the model's flexibility for complex data structure. Experimental results demonstrate that CCGL has achieved excellent performance compared to state-of-the-art competitors.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12071
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
Zeng, Chusheng
Wang, Bocheng
Yuan, Jinghui
Wang, Rong
Chen, Mulin
Machine Learning
Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used to improve learning diversity, but commonly used random augmentation methods may destroy inherent semantics and cause noise; 2) the fixed positive and negative sample selection strategy is limited to deal with complex real data, thereby impeding the model's capability to capture fine-grained patterns and relationships. To reduce these problems, we propose the Clustering-guided Curriculum Graph contrastive Learning (CCGL) framework. CCGL uses clustering entropy as the guidance of the following graph augmentation and contrastive learning. Specifically, according to the clustering entropy, the intra-class edges and important features are emphasized in augmentation. Then, a multi-task curriculum learning scheme is proposed, which employs the clustering guidance to shift the focus from the discrimination task to the clustering task. In this way, the sample selection strategy of contrastive learning can be adjusted adaptively from early to late stage, which enhances the model's flexibility for complex data structure. Experimental results demonstrate that CCGL has achieved excellent performance compared to state-of-the-art competitors.
title Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
topic Machine Learning
url https://arxiv.org/abs/2408.12071