Text Enriched Sparse Hyperbolic Graph Convolutional Networks

TL;DR

This paper introduces TESH-GCN, a novel hyperbolic graph neural network that leverages semantic and metapath information from text to improve link prediction in heterogeneous networks, outperforming existing methods in accuracy and efficiency.

Contribution

The paper proposes a new hyperbolic GCN model that incorporates semantic signals and metapath structures, enhancing robustness and reducing training time compared to prior hyperbolic approaches.

Findings

Outperforms state-of-the-art on link prediction tasks

Reduces training time and model parameters

Demonstrates robustness to noise in graph and text data

Abstract

Heterogeneous networks, which connect informative nodes containing text with different edge types, are routinely used to store and process information in various real-world applications. Graph Neural Networks (GNNs) and their hyperbolic variants provide a promising approach to encode such networks in a low-dimensional latent space through neighborhood aggregation and hierarchical feature extraction, respectively. However, these approaches typically ignore metapath structures and the available semantic information. Furthermore, these approaches are sensitive to the noise present in the training data. To tackle these limitations, in this paper, we propose Text Enriched Sparse Hyperbolic Graph Convolution Network (TESH-GCN) to capture the graph's metapath structures using semantic signals and further improve prediction in large heterogeneous graphs. In TESH-GCN, we extract semantic node information, which successively acts as a connection signal to extract relevant nodes' local neighborhood and graph-level metapath features from the sparse adjacency tensor in a reformulated hyperbolic graph convolution layer. These extracted features in conjunction with semantic features from the language model (for robustness) are used for the final downstream task. Experiments on various heterogeneous graph datasets show that our model outperforms the current state-of-the-art approaches by a large margin on the task of link prediction. We also report a reduction in both the training time and model parameters compared to the existing hyperbolic approaches through a reformulated hyperbolic graph convolution. Furthermore, we illustrate the robustness of our model by experimenting with different levels of simulated noise in both the graph structure and text, and also, present a mechanism to explain TESH-GCN's prediction by analyzing the extracted metapaths.