RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Junyu, Shi, Long, Chen, Badong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909044518682624
author Chen, Junyu
Shi, Long
Chen, Badong
author_facet Chen, Junyu
Shi, Long
Chen, Badong
contents Graph Neural Networks (GNNs) have exhibited remarkable efficacy in learning from multi-view graph data. In the framework of multi-view graph neural networks, a critical challenge lies in effectively combining diverse views, where each view has distinct graph structure features (GSFs). Existing approaches to this challenge primarily focus on two aspects: 1) prioritizing the most important GSFs, 2) utilizing GNNs for feature aggregation. However, prioritizing the most important GSFs can lead to limited feature diversity, and existing GNN-based aggregation strategies equally treat each view without considering view quality. To address these issues, we propose a novel Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation (RSEA-MVGNN). Firstly, we estimate view-specific uncertainty employing subjective logic. Based on this uncertainty, we design reliable structural enhancement by feature de-correlation algorithm. This approach enables each enhancement to focus on different GSFs, thereby achieving diverse feature representation in the enhanced structure. Secondly, the model learns view-specific beliefs and uncertainty as opinions, which are utilized to evaluate view quality. Based on these opinions, the model enables high-quality views to dominate GNN aggregation, thereby facilitating representation learning. Experimental results conducted on five real-world datasets demonstrate that RSEA-MVGNN outperforms several state-of-the-art GNN-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2408_07331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation
Chen, Junyu
Shi, Long
Chen, Badong
Machine Learning
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in learning from multi-view graph data. In the framework of multi-view graph neural networks, a critical challenge lies in effectively combining diverse views, where each view has distinct graph structure features (GSFs). Existing approaches to this challenge primarily focus on two aspects: 1) prioritizing the most important GSFs, 2) utilizing GNNs for feature aggregation. However, prioritizing the most important GSFs can lead to limited feature diversity, and existing GNN-based aggregation strategies equally treat each view without considering view quality. To address these issues, we propose a novel Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation (RSEA-MVGNN). Firstly, we estimate view-specific uncertainty employing subjective logic. Based on this uncertainty, we design reliable structural enhancement by feature de-correlation algorithm. This approach enables each enhancement to focus on different GSFs, thereby achieving diverse feature representation in the enhanced structure. Secondly, the model learns view-specific beliefs and uncertainty as opinions, which are utilized to evaluate view quality. Based on these opinions, the model enables high-quality views to dominate GNN aggregation, thereby facilitating representation learning. Experimental results conducted on five real-world datasets demonstrate that RSEA-MVGNN outperforms several state-of-the-art GNN-based methods.
title RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation
topic Machine Learning
url https://arxiv.org/abs/2408.07331