Multi-view graph structure learning using subspace merging on Grassmann manifold

TL;DR

This paper introduces MV-GSL, a multi-view graph structure learning method that merges different graph learning approaches on the Grassmann manifold to enhance graph quality for improved learning outcomes.

Contribution

The paper proposes a novel multi-view graph structure learning framework using subspace merging on Grassmann manifold, improving graph quality over existing methods.

Findings

MV-GSL outperforms single-view methods on benchmark datasets

The approach effectively combines multiple graph learning techniques

Experimental results demonstrate improved graph quality and learning performance

Abstract

Many successful learning algorithms have been recently developed to represent graph-structured data. For example, Graph Neural Networks (GNNs) have achieved considerable successes in various tasks such as node classification, graph classification, and link prediction. However, these methods are highly dependent on the quality of the input graph structure. One used approach to alleviate this problem is to learn the graph structure instead of relying on a manually designed graph. In this paper, we introduce a new graph structure learning approach using multi-view learning, named MV-GSL (Multi-View Graph Structure Learning), in which we aggregate different graph structure learning methods using subspace merging on Grassmann manifold to improve the quality of the learned graph structures. Extensive experiments are performed to evaluate the effectiveness of the proposed method on two benchmark datasets, Cora and Citeseer. Our experiments show that the proposed method has promising performance compared to single and other combined graph structure learning methods.