arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03032cs.SIcs.AI
收藏

超图中节点的边依赖标签分类

Classification of Edge-dependent Labels of Nodes in Hypergraphs

KAIST(韩国科学技术院);Carnegie Mellon University(卡内基梅隆大学)

Minyoung Choe, Sunwoo Kim, Jaemin Yoo, Kijung Shin

AI总结:

本文提出超图节点的边依赖标签分类新问题,并设计 WHATsNet 利用超边内相对中心性位置编码区分节点角色,在六个数据集上优于十种方法并成功用于三类任务。

摘要:

超图是一种由节点和超边组成的数据结构,其中每条超边都是任意大小的节点子集。由于超边大小具有灵活性,超图比普通图更自然、更准确地表示群体交互(例如两名以上作者的共同作者关系)。有趣的是,许多被建模为超图的真实世界系统都包含边依赖节点标签,即随超边不同而变化的节点标签。例如,在共同作者关系数据集中,同一作者(即一个节点)在一篇论文(即一条超边)中可能是主要作者,而在另一篇论文(即另一条超边)中则是通讯作者。在本研究中,我们将边依赖节点标签分类作为一个新问题提出。该问题可作为近期备受关注的超图神经网络的基准任务,而且边依赖节点标签的有用性也已在多种应用中得到验证。为解决这一问题,我们提出 WHATsNet,这是一种新颖的超图神经网络,通过反映同一节点在其所参与的不同超边中的变化重要性,依据超边对该节点进行不同表示。为此,WHATsNet 使用节点在每条超边内的相对中心性作为位置编码,对节点之间的关系进行建模。在实验中,我们证明 WHATsNet 在六个真实世界超图上显著且一致地优于十个竞争对手;我们还展示了 WHATsNet 在(a)排序聚合、(b)节点聚类和(c)商品退货预测方面的成功应用。

英文摘要:

A hypergraph is a data structure composed of nodes and hyperedges, where each hyperedge is an any-sized subset of nodes. Due to the flexibility in hyperedge size, hypergraphs represent group interactions (e.g., co-authorship by more than two authors) more naturally and accurately than ordinary graphs. Interestingly, many real-world systems modeled as hypergraphs contain edge-dependent node labels, i.e., node labels that vary depending on hyperedges. For example, on co-authorship datasets, the same author (i.e., a node) can be the primary author in a paper (i.e., a hyperedge) but the corresponding author in another paper (i.e., another hyperedge). In this work, we introduce a classification of edge-dependent node labels as a new problem. This problem can be used as a benchmark task for hypergraph neural networks, which recently have attracted great attention, and also the usefulness of edge-dependent node labels has been verified in various applications. To tackle this problem, we propose WHATsNet, a novel hypergraph neural network that represents the same node differently depending on the hyperedges it participates in by reflecting its varying importance in the hyperedges. To this end, WHATsNet models the relations between nodes within each hyperedge, using their relative centrality as positional encodings. In our experiments, we demonstrate that WHATsNet significantly and consistently outperforms ten competitors on six real-world hypergraphs, and we also show successful applications of WHATsNet to (a) ranking aggregation, (b) node clustering, and (c) product return prediction.

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。

↑