Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification

TL;DR

This paper introduces a novel semantic graph neural network framework that adaptively learns optimal graph structures using multi-measure attention, significantly improving semi-supervised classification performance.

Contribution

The paper proposes a new framework that encodes semantic interactions, employs multi-measure attention for adaptive similarity evaluation, and fuses learned graphs with GNNs for enhanced semi-supervised classification.

Findings

Effective on six real-world datasets

Outperforms existing GNN methods

Ablation studies confirm component contributions

Abstract

Graph Neural Networks (GNNs) have attracted increasing attention in recent years and have achieved excellent performance in semi-supervised node classification tasks. The success of most GNNs relies on one fundamental assumption, i.e., the original graph structure data is available. However, recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph, making it necessary to learn comprehensive and robust graph structures for downstream tasks, rather than relying only on the raw graph structure. In light of this, we seek to learn optimal graph structures for downstream tasks and propose a novel framework for semi-supervised classification. Specifically, based on the structural context information of graph and node representations, we encode the complex interactions in semantics and generate semantic graphs to preserve the global structure. Moreover, we develop a novel multi-measure attention layer to optimize the similarity rather than prescribing it a priori, so that the similarity can be adaptively evaluated by integrating measures. These graphs are fused and optimized together with GNN towards semi-supervised classification objective. Extensive experiments and ablation studies on six real-world datasets clearly demonstrate the effectiveness of our proposed model and the contribution of each component.