Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph Clustering

Zichen Wen, Tianyi Wu, Yazhou Ren, Yawen Ling, Chenhang Cui, Xiaorong Pu, Lifang He

Abstract: Multi-view clustering is an important machine learning task for multi-media data, encompassing various domains such as images, videos, and texts. Moreover, with the growing abundance of graph data, the significance of multi-view graph clustering (MVGC) has become evident. Most existing methods focus on graph neural networks (GNNs) to extract information from both graph structure and feature data to learn distinguishable node representations. However, traditional GNNs are designed with the assumption of homophilous graphs, making them unsuitable for widely prevalent heterophilous graphs. Several techniques have been introduced to enhance GNNs for heterophilous graphs. While these methods partially mitigate the heterophilous graph issue, they often neglect the advantages of traditional GNNs, such as their simplicity, interpretability, and efficiency. In this paper, we propose a novel multi-view graph clustering method based on dual-optimized adaptive graph reconstruction, named DOAGC. It mainly aims to reconstruct the graph structure adapted to traditional GNNs to deal with heterophilous graph issues while maintaining the advantages of traditional GNNs. Specifically, we first develop an adaptive graph reconstruction mechanism that accounts for node correlation and original structural information. To further optimize the reconstruction graph, we design a dual optimization strategy and demonstrate the feasibility of our optimization strategy through mutual information theory. Numerous experiments demonstrate that DOAGC effectively mitigates the heterophilous graph problem.

Primary Subject Area: [Content] Multimodal Fusion

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: In multimedia/multimodal processing, data often come in various forms such as images, text, audio, and video, each representing different views or modalities of information. This work contributes to multimedia/multimodal processing by addressing the challenge of effectively clustering graph data from multiple views or modalities. Traditional methods for graph clustering often struggle with heterophilous graphs, which contain nodes with varying types of connections and attributes. The proposed method, DOAGC, leverages a dual optimization strategy to adaptively reconstruct the graph structure, considering both node correlation and original structural information， which effectively tackles the heterophilous graph problem inherent in multi-view graph clustering.

Submission Number: 1470