DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

TL;DR

DiffMG introduces a differentiable neural architecture search framework to automatically discover complex meta graphs in heterogeneous information networks, enhancing GNN performance and efficiency for various downstream tasks.

Contribution

The paper presents a novel differentiable NAS approach for meta graph search in HINs, enabling automatic discovery of complex semantic relations for improved GNNs.

Findings

Outperforms state-of-the-art heterogeneous GNNs on multiple tasks.

Achieves higher search efficiency compared to existing NAS algorithms.

Effectively filters irrelevant edge types, improving message passing relevance.

Abstract

In this paper, we propose a novel framework to automatically utilize task-dependent semantic information which is encoded in heterogeneous information networks (HINs). Specifically, we search for a meta graph, which can capture more complex semantic relations than a meta path, to determine how graph neural networks (GNNs) propagate messages along different types of edges. We formalize the problem within the framework of neural architecture search (NAS) and then perform the search in a differentiable manner. We design an expressive search space in the form of a directed acyclic graph (DAG) to represent candidate meta graphs for a HIN, and we propose task-dependent type constraint to filter out those edge types along which message passing has no effect on the representations of nodes that are related to the downstream task. The size of the search space we define is huge, so we further propose a novel and efficient search algorithm to make the total search cost on a par with training a single GNN once. Compared with existing popular NAS algorithms, our proposed search algorithm improves the search efficiency. We conduct extensive experiments on different HINs and downstream tasks to evaluate our method, and experimental results show that our method can outperform state-of-the-art heterogeneous GNNs and also improves efficiency compared with those methods which can implicitly learn meta paths.