ISHNE: Influence Self-attention for Heterogeneous Network Embedding

TL;DR

This paper introduces ISHNE, a novel influence self-attention network for heterogeneous network embedding that models complex relations and interactions, outperforming existing methods in capturing network heterogeneity.

Contribution

The paper proposes a new influence self-attention mechanism and a unified meta-path relation fusion framework for better heterogeneous network modeling.

Findings

Achieves higher accuracy than state-of-the-art baselines.

Effectively models heterogeneous relations and interactions.

Demonstrates promising results on complex network structures.

Abstract

In recent years, Graph Neural Networks has received enormous attention from academia for its huge potential of modeling the network traits such as macrostructure and single node attributes. However, prior mainstream works mainly focus on homogeneous network and lack the capacity to characterize the network heterogeneous property. Besides, most previous literature cannot model the influence under microscope vision, making it infeasible to model the joint relation between the heterogeneity and mutual interaction within multiple relation type. In this paper, we propose an Influence Self-attention network to address the difficulties mentioned above. To model heterogeneity and mutual interaction, we redesign attention mechanism with influence factor on the single-type relation level, which learns the importance coefficient from its adjacent neighbors under the same meta-path based patterns. To incorporate the heterogeneous meta-path in a unified dimension, we developed a self-attention based framework for meta-path relation fusion according to the learned meta-path coefficient. Our experimental results demonstrate that our framework not only achieve higher results than current state-of-the-art baselines, but also show promising vision on depicting heterogeneous interactive relations under complicated network structure.