Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion

2026-03-20

AI Summary

This work addresses limitations in existing graph convolutional network–based multi-view methods, which struggle to effectively model consistency across nodes, features, and views due to constraints in topology construction, feature alignment, and view fusion. To overcome these challenges, the paper proposes MGCN-FLC, a novel framework that adaptively constructs graph topology using the granular ball algorithm and introduces a consistency-driven feature enhancement mechanism alongside an interactive multi-view fusion strategy. These components jointly optimize consistency information at the three levels in a systematic manner. Extensive experiments on nine benchmark datasets for semi-supervised node classification demonstrate that the proposed method significantly outperforms state-of-the-art models, yielding substantial improvements in both embedding quality and classification performance.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The effective utilization of consistency is crucial for multi-view learning. GCNs leverage node connections to propagate information across the graph, facilitating the exploitation of consistency in multi-view data. However, most existing GCN-based multi-view methods suffer from several limitations. First, current approaches predominantly rely on KNN for topology construction, where the artificial selection of the k value significantly constrains the effective exploitation of inter-node consistency. Second, the inter-feature consistency within individual views is often overlooked, which adversely affects the quality of the final embedding representations. Moreover, these methods fail to fully utilize inter-view consistency as the fusion of embedded representations from multiple views is often implemented after the intra-view graph convolutional operation. Collectively, these issues limit the model's capacity to fully capture inter-node, inter-feature and inter-view consistency. To address these issues, this paper proposes the multi-view graph convolutional network with fully leveraging consistency via GB-based topology construction, feature enhancement and interactive fusion (MGCN-FLC). MGCN-FLC can fully utilize three types of consistency via the following three modules to enhance learning ability:The topology construction module based on the granular ball algorithm, which clusters nodes into granular balls with high internal similarity to capture inter-node consistency;The feature enhancement module that improves feature representations by capturing inter-feature consistency;The interactive fusion module that enables each view to deeply interact with all other views, thereby obtaining more comprehensive inter-view consistency. Experimental results on nine datasets show that the proposed MGCN-FLC outperforms state-of-the-art semi-supervised node classification methods.

Problem

• multi-view learning
• graph convolutional network
• consistency
• topology construction
• feature enhancement

Innovation

• multi-view graph convolutional network
• granular-ball topology
• feature enhancement
• interactive fusion
• consistency exploitation