When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shen, Zhixiang, Kang, Zhao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917910752002048
author Shen, Zhixiang
Kang, Zhao
author_facet Shen, Zhixiang
Kang, Zhao
contents Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this paper, we define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning
Shen, Zhixiang
Kang, Zhao
Machine Learning
Artificial Intelligence
Social and Information Networks
Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this paper, we define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.
title When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2409.00687