Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution

TL;DR

This paper introduces CoMGNN and ST-CoMGNN, novel graph neural network models that incorporate meta attention and co-evolution of node and edge states to better capture complex heterogeneity and spatiotemporal dynamics in real-world graphs.

Contribution

The paper proposes CoMGNN and ST-CoMGNN, pioneering models that integrate meta attention with co-evolving node and edge features for heterogeneous graphs.

Findings

Models outperform state-of-the-art methods on large-scale datasets

Effective in capturing heterogeneity and spatiotemporal patterns

Demonstrates significant improvements in modeling complex graph data

Abstract

Graph neural networks have become an important tool for modeling structured data. In many real-world systems, intricate hidden information may exist, e.g., heterogeneity in nodes/edges, static node/edge attributes, and spatiotemporal node/edge features. However, most existing methods only take part of the information into consideration. In this paper, we present the Co-evolved Meta Graph Neural Network (CoMGNN), which applies meta graph attention to heterogeneous graphs with co-evolution of node and edge states. We further propose a spatiotemporal adaption of CoMGNN (ST-CoMGNN) for modeling spatiotemporal patterns on nodes and edges. We conduct experiments on two large-scale real-world datasets. Experimental results show that our models significantly outperform the state-of-the-art methods, demonstrating the effectiveness of encoding diverse information from different aspects.