DPHGNN：双视角超图神经网络
DPHGNN: A Dual Perspective Hypergraph Neural Networks
AI总结：
DPHGNN通过双视角等变算子学习融合低阶图特征与高阶超图结构，在八个数据集上超越七个基线，并在电商RTO预测中提升约7%宏F1分数。
摘要：
在超图上进行消息传递已成为学习超节点间高阶相关性的标准框架。近期提出的超图神经网络（HGNN）根据其设计选择可分为空间方法和谱方法。在本工作中，我们分析了超图拓扑变化对HGNN次优性能的影响，并提出DPHGNN，一种新颖的双视角HGNN，通过引入等变算子学习来捕获低阶语义，从而诱导拓扑感知的空间和谱归纳偏置。DPHGNN采用统一框架，将来自底层图的低阶显式特征表示动态融合到叠加的超图结构中。我们在八个基准超图数据集上对DPHGNN进行半监督超节点分类任务的基准测试，并获得了优于七个最先进基线的性能。我们还提供了理论框架和合成超图同构测试，以表达空间HGNN的能力，并量化DPHGNN超越广义Weisfeiler-Leman（1-GWL）测试的表达力。最后，DPHGNN已被我们的合作电商公司部署用于退货至原点（RTO）预测任务，其宏F1分数比最佳基线高出约7%。
英文摘要：
Message passing on hypergraphs has been a standard framework for learning higher-order correlations between hypernodes. Recently-proposed hypergraph neural networks (HGNNs) can be categorized into spatial and spectral methods based on their design choices. In this work, we analyze the impact of change in hypergraph topology on the suboptimal performance of HGNNs and propose DPHGNN, a novel dual-perspective HGNN that introduces equivariant operator learning to capture lower-order semantics by inducing topology-aware spatial and spectral inductive biases. DPHGNN employs a unified framework to dynamically fuse lower-order explicit feature representations from the underlying graph into the super-imposed hypergraph structure. We benchmark DPHGNN over eight benchmark hypergraph datasets for the semi-supervised hypernode classification task and obtain superior performance compared to seven state-of-the-art baselines. We also provide a theoretical framework and a synthetic hypergraph isomorphism test to express the power of spatial HGNNs and quantify the expressivity of DPHGNN beyond the Generalized Weisfeiler Leman (1-GWL) test. Finally, DPHGNN was deployed by our partner e-commerce company for the Return-to-Origin (RTO) prediction task, which shows ~7% higher macro F1-Score than the best baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
