一般化
层
数学
超图
表现力
离散数学
理论计算机科学
回注、回注、回注
代数数
度量(数据仓库)
相关性(法律)
拉普拉斯算子
概率测度
计算机科学
方案(数学)
操作员(生物学)
代数结构
人工神经网络
拓扑(电路)
域代数上的
构造(python库)
归纳逻辑编程
直接限值
班级(哲学)
群(周期表)
人工智能
极限(数学)
功率(物理)
作者
Emanuele Mule,Fiorini, Stefano,Antonio Purificato,Federico Siciliano,Stefano Coniglio,Fabrizio Silvestri
标识
DOI:10.48550/arxiv.2510.04727
摘要
Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed hypergraphs, which can model oriented group interactions, remains largely under-explored despite its relevance for many applications. Recent approaches in this direction often exhibit an implicit bias toward homophily, which limits their effectiveness in heterophilic settings. Rooted in the algebraic topology notion of Cellular Sheaves, Sheaf Neural Networks (SNNs) were introduced as an effective solution to circumvent such a drawback. While a generalization to hypergraphs is known, it is only suitable for undirected hypergraphs, failing to tackle the directed case. In this work, we introduce Directional Sheaf Hypergraph Networks (DSHN), a framework integrating sheaf theory with a principled treatment of asymmetric relations within a hypergraph. From it, we construct the Directed Sheaf Hypergraph Laplacian, a complex-valued operator by which we unify and generalize many existing Laplacian matrices proposed in the graph- and hypergraph-learning literature. Across 7 real-world datasets and against 13 baselines, DSHN achieves relative accuracy gains from 2% up to 20%, showing how a principled treatment of directionality in hypergraphs, combined with the expressive power of sheaves, can substantially improve performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI