Edge-featured Graph Neural Architecture Search

TL;DR

This paper introduces a novel neural architecture search method for graph neural networks that incorporates edge features, enabling the discovery of more effective GNN architectures with higher performance across various graph tasks.

Contribution

It proposes a new search space and differentiable search strategy that explicitly models edge features and their interactions with node features in GNNs.

Findings

EGNAS outperforms state-of-the-art GNNs on multiple datasets.

Incorporating edge features improves message passing effectiveness.

The method efficiently explores complex feature dependencies.

Abstract

Graph neural networks (GNNs) have been successfully applied to learning representation on graphs in many relational tasks. Recently, researchers study neural architecture search (NAS) to reduce the dependence of human expertise and explore better GNN architectures, but they over-emphasize entity features and ignore latent relation information concealed in the edges. To solve this problem, we incorporate edge features into graph search space and propose Edge-featured Graph Neural Architecture Search to find the optimal GNN architecture. Specifically, we design rich entity and edge updating operations to learn high-order representations, which convey more generic message passing mechanisms. Moreover, the architecture topology in our search space allows to explore complex feature dependence of both entities and edges, which can be efficiently optimized by differentiable search strategy. Experiments at three graph tasks on six datasets show EGNAS can search better GNNs with higher performance than current state-of-the-art human-designed and searched-based GNNs.