用经典超图特征提升图模型对高阶关系的建模能力
Enhancing the Utility of Higher-Order Information in Relational Learning
- 将超图特性编码后输入标准图神经网络，替代复杂超图网络
- 在多个数据集上，该方法性能优于原生超图模型
- 适合想高效利用高阶关系的研究者使用
高阶信息在许多关系学习场景中至关重要，这些场景中的关系超越了成对交互。超图为建模此类关系提供了自然框架，推动了图神经网络架构向超图的扩展。然而，超图架构与标准图模型之间的对比仍有限。本文系统评估了几种超图级和图级架构在利用高阶信息方面的有效性。结果表明，将图级架构应用于超图展开时，往往优于原生超图级模型，即使输入本应以超图形式表示。作为替代方案，我们提出基于经典超图特性的超图级编码。这些编码虽对超图模型提升有限，但与图级模型结合后带来显著性能提升。理论分析表明，超图级编码可证明性地增强消息传递图神经网络的表征能力，超越其图级对应模型。
原文摘要 · Abstract (English)
Higher-order information is crucial for relational learning in many domains where relationships extend beyond pairwise interactions. Hypergraphs provide a natural framework for modeling such relationships, which has motivated recent extensions of graph neural network architectures to hypergraphs. However, comparisons between hypergraph architectures and standard graph-level models remain limited. In this work, we systematically evaluate a selection of hypergraph-level and graph-level architectures, to determine their effectiveness in leveraging higher-order information in relational learning. Our results show that graph-level architectures applied to hypergraph expansions often outperform hypergraph-level ones, even on inputs that are naturally parametrized as hypergraphs. As an alternative approach for leveraging higher-order information, we propose hypergraph-level encodings based on classical hypergraph characteristics. While these encodings do not significantly improve hypergraph architectures, they yield substantial performance gains when combined with graph-level models. Our theoretical analysis shows that hypergraph-level encodings provably increase the representational power of message-passing graph neural networks beyond that of their graph-level counterparts.
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。