节点与超边上的有效且高效的属性超图嵌入
Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges
AI总结：
提出 SAHE 方法，通过引入高阶相似性度量 HMS-N 和 HMS-E 并设计高效优化算法，统一实现属性超图节点与超边嵌入，在嵌入质量和计算效率上显著优于现有方法。
摘要：
属性超图包含具有属性的节点和连接不同数量节点的超边。属性超图节点与超边嵌入（AHNEE）将节点和超边映射为紧凑向量，用于节点分类、超边链接预测和超边分类等重要任务。由于属性超图的复杂性以及需要同时嵌入节点和超边，尤其是在大规模数据中，生成高质量嵌入具有挑战性。现有解决方案通常只关注节点或缺乏对属性超图的原生支持，导致质量较差，且在大型属性超图上难以扩展。我们提出 SAHE，一种高效且有效的方法，统一节点和超边嵌入以进行 AHNEE 计算，通过全面的嵌入形式化和算法设计推进最新技术。首先，我们引入两种高阶相似性度量 HMS-N 和 HMS-E，分别捕获节点对和超边对之间的相似性。这些度量考虑了在包含基于属性的超边的扩展超图中的多跳连接和全局拓扑。SAHE 将 AHNEE 目标形式化为联合保留所有节点对的 HMS-N 和 HMS-E 相似性。直接优化计算成本高昂，因此我们分析并统一了所有节点对 HMS-N 和 HMS-E 的核心近似以同时求解。为提升效率，我们设计了若干非平凡优化，避免迭代物化大型稠密矩阵，同时保持高质量结果。在多种属性超图和 3 个下游任务上与 11 个基线方法对比的广泛实验表明，SAHE 在嵌入质量上始终优于现有方法，且速度最多快几个数量级。
英文摘要：
An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes and hyperedges to compact vectors for use in important tasks such as node classification, hyperedge link prediction, and hyperedge classification. Generating high-quality embeddings is challenging due to the complexity of attributed hypergraphs and the need to embed both nodes and hyperedges, especially in large-scale data. Existing solutions often fall short by focusing only on nodes or lacking native support for attributed hypergraphs, leading to inferior quality, and struggle with scalability on large attributed hypergraphs. We propose SAHE, an efficient and effective approach that unifies node and hyperedge embeddings for AHNEE computation, advancing the state of the art via comprehensive embedding formulations and algorithmic designs. First, we introduce two higher-order similarity measures, HMS-N and HMS-E, to capture similarities between node pairs and hyperedge pairs, respectively. These measures consider multi-hop connections and global topology within an extended hypergraph that incorporates attribute-based hyperedges. SAHE formulates the AHNEE objective to jointly preserve all-pair HMS-N and HMS-N similarities. Direct optimization is computationally expensive, so we analyze and unify core approximations of all-pair HMS-N and HMS-N to solve them simultaneously. To enhance efficiency, we design several non-trivial optimizations that avoid iteratively materializing large dense matrices while maintaining high-quality results. Extensive experiments on diverse attributed hypergraphs and 3 downstream tasks, compared against 11 baselines, show that SAHE consistently outperforms existing methods in embedding quality and is up to orders of magnitude faster.
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。
