通过多样化采样提升图注意力模型对高阶关系的捕捉能力
HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling
- 用多样性感知的k跳采样构建高阶注意力矩阵
- 在所有节点分类数据集上提升至少5%准确率
- 适合需要挖掘复杂图结构关系的研究者
图模型广泛用于刻画现实系统中潜在变量之间的关系，消息传递神经网络（MPNNs）被普遍用于学习这些结构以支持下游任务。尽管基于边的MPNN能有效捕捉局部交互，但其表达能力在理论上受限，难以发现高阶关系。本文提出高阶图注意力（HoGA）模块，通过采样子图构建k阶注意力矩阵，旨在最大化特征向量间的多样性。与现有方法贪婪地重复采样相似高阶关系不同，HoGA聚焦于高阶拓扑中的多样化模式，减少冗余并扩展可捕获的子结构范围。将HoGA应用于两个单跳注意力模型，在所有基准节点分类数据集上均取得至少5%的准确率提升，并在八个数据集中的六个上超越近期基线。代码已公开于https://github.com/TB862/Higher_Order。
原文摘要 · Abstract (English)
Graphs model latent variable relationships in many real-world systems, and Message Passing Neural Networks (MPNNs) are widely used to learn such structures for downstream tasks. While edge-based MPNNs effectively capture local interactions, their expressive power is theoretically bounded, limiting the discovery of higher-order relationships. We introduce the Higher-Order Graph Attention (HoGA) module, which constructs a k-order attention matrix by sampling subgraphs to maximize diversity among feature vectors. Unlike existing higher-order attention methods that greedily resample similar k-order relationships, HoGA targets diverse modalities in higher-order topology, reducing redundancy and expanding the range of captured substructures. Applied to two single-hop attention models, HoGA achieves at least a 5% accuracy gain on all benchmark node classification datasets and outperforms recent baselines on six of eight datasets. Code is available at https://github.com/TB862/Higher_Order.
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。