提出DiRW方法，让图神经网络更好处理有向图中的异质连接。
DiRW: Path-Aware Digraph Learning for Heterophily
- 基于方向感知的随机游走采样路径，无需权重优化
- 在9个数据集上显著提升模型性能，达当前最优
- 可直接插入现有空间型图神经网络，适用性强
图神经网络（GNN）是处理图结构数据的强大工具，但多数方法针对无向图，忽视了有向图（digraph）中丰富的边信息。实际上，有向图广泛应用于现实场景，并被证实有助于缓解异质性挑战。尽管已有进展，现有的空间和谱域有向图神经网络因学习机制复杂且依赖高质量拓扑，导致效率低、表现不稳定。为此，我们提出定向随机游走（DiRW），一种适用于大多数空间型有向图神经网络的即插即用策略，也是一种创新的有向图学习范式。具体地，它通过节点特征和拓扑信息，在不使用权重的情况下，从游走概率、长度和数量三个维度优化方向感知路径采样。在此基础上，DiRW引入节点级可学习路径聚合器，生成通用节点表示。在9个数据集上的大量实验表明：(1) 可作为即插即用策略增强多数空间型方法；(2) 作为新范式达到当前最优性能。代码与数据已公开于https://github.com/dhsiuu/DiRW。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。