用神经网络检测超图中异常的高阶关系，无需标签数据。
Hyperedge Anomaly Detection with Hypergraph Neural Network
- 构建端到端超图神经网络，自动学习高阶关联模式。
- 在多个真实数据集上验证，能有效识别异常超边。
- 适合处理社交网络、知识图谱等复杂关系场景。
超图是一种能够建模数据实体间高阶关联的数据结构，相比传统图只能表示成对关系，超图可关联任意数量实体，在诸多现实应用中至关重要。尽管超图学习已在节点分类、链接预测等问题上得到充分研究，但针对超图的异常检测研究仍较少。异常检测旨在识别偏离正常模式的事件，应用于超图可发现异常的高阶关联。本文提出一种基于超图神经网络的端到端模型，用于识别超图中的异常关联。该算法采用无监督方式，无需任何标注数据。在多个真实数据集上的大量实验表明，所提模型在检测异常超边方面具有显著有效性。
原文摘要 · Abstract (English)
Hypergraph is a data structure that enables us to model higher-order associations among data entities. Conventional graph-structured data can represent pairwise relationships only, whereas hypergraph enables us to associate any number of entities, which is essential in many real-life applications. Hypergraph learning algorithms have been well-studied for numerous problem settings, such as node classification, link prediction, etc. However, much less research has been conducted on anomaly detection from hypergraphs. Anomaly detection identifies events that deviate from the usual pattern and can be applied to hypergraphs to detect unusual higher-order associations. In this work, we propose an end-to-end hypergraph neural network-based model for identifying anomalous associations in a hypergraph. Our proposed algorithm operates in an unsupervised manner without requiring any labeled data. Extensive experimentation on several real-life datasets demonstrates the effectiveness of our model in detecting anomalous hyperedges.
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。