DiRW: Path-Aware Digraph Learning for Heterophily

TL;DR

DiRW introduces a novel, efficient path-aware sampling strategy for directed graph neural networks, significantly improving performance on heterophilic digraphs and serving as a versatile plug-and-play enhancement.

Contribution

It proposes DiRW, a new digraph learning paradigm with a direction-aware path sampler and node-wise aggregator, addressing efficiency and stability issues in existing methods.

Findings

Enhances spatial-based DiGNNs as a plug-and-play strategy.

Achieves state-of-the-art performance on 9 datasets.

Demonstrates robustness and efficiency in heterophily scenarios.

Abstract

Recently, graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data. However, most approaches are tailored for undirected graphs, neglecting the abundant information in the edges of directed graphs (digraphs). In fact, digraphs are widely applied in the real world and confirmed to address heterophily challenges. Despite recent advancements, existing spatial- and spectral-based DiGNNs have limitations due to their complex learning mechanisms and reliance on high-quality topology, resulting in low efficiency and unstable performance. To address these issues, we propose Directed Random Walk (DiRW), a plug-and-play strategy for most spatial-based DiGNNs and also an innovative model which offers a new digraph learning paradigm. Specifically, it utilizes a direction-aware path sampler optimized from the perspectives of walk probability, length, and number in a weight-free manner by considering node profiles and topologies. Building upon this, DiRW incorporates a node-wise learnable path aggregator for generalized node representations. Extensive experiments on 9 datasets demonstrate that DiRW: (1) enhances most spatial-based methods as a plug-and-play strategy; (2) achieves SOTA performance as a new digraph learning paradigm. The source code and data are available at https://github.com/dhsiuu/DiRW.