当连接并不意味着相似：绘制SNAP-KG在流式实体集成中的同质性边界
When Connected Does Not Mean Similar: Charting the Homophily Boundary of SNAP-KG for Streaming Entity Integration
查看机构详情
- Rensselaer Polytechnic Institute（伦斯勒理工学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文探讨SNAP-KG在无同质性关系时聚类性能骤降，指出同质性假设是方法家族共性，并提出未来通过蒸馏异质性感知教师模型以扩展其适用性。
中文摘要 AI 辅助
SNAP-KG是一个框架，用于在增长的知识图谱（KG）中，仅利用新到达实体的原始特征，将其分配到语义社区，无需图访问，也无需在推理时重新训练。该框架在五个多视图基准和一个包含240万节点的OGB-WikiKG2知识图谱上进行了评估。在这些数据集中，每个至少有一个图视图是同质性的，这意味着连接的节点通常属于同一类别，SNAP-KG在所有数据集上均表现良好。本文探讨了在该设置之外的情况。我们将评估扩展到三个异质性图（Texas、Wisconsin、Chameleon），并测量每个视图的边同质性。当没有同质性视图可用时，SNAP-KG及其原始评估中使用的转导基线的聚类质量都会急剧下降。决定这一点的因素是关系的同质性，而非关系的数量。多视图融合仍然有帮助，但仅当至少有一个同质性关系提供可靠基础时。因此，同质性假设是整个方法家族共有的，而非SNAP-KG特有。我们认为异质性多视图聚类是一个独立的研究问题，不在本文范围内。作为未来工作，我们概述了如何将异质性感知的教师模型蒸馏到SNAP-KG的投影器中，以同时服务于同质性和异质性知识图谱。
英文摘要
SNAP-KG is a framework for assigning newly arriving entities to semantic communities in a growing knowledge graph (KG) using only their raw features, with no graph access and no retraining at inference time. It was evaluated on five multi-view benchmarks and a 2.4M-node OGB-WikiKG2 KG. In each of these datasets, at least one graph view is homophilous, meaning that connected nodes usually belong to the same class, and SNAP-KG performs well on all of them. This paper asks what happens outside that setting. We extend the evaluation to three heterophilous graphs (Texas, Wisconsin, Chameleon) and measure the edge homophily of every view. When no homophilous view is available, clustering quality drops sharply for both SNAP-KG and the transductive baselines used in its original evaluation. What decides this is the homophily of the relation, not the number of relations. Multi-view fusion still helps, but only when at least one homophilous relation provides a reliable foundation. The homophily assumption is therefore shared by the whole method family, not specific to SNAP-KG. We argue that heterophilous multi-view clustering is a separate research problem, outside the scope of this work. As future work, we outline how a heterophily-aware teacher could be distilled into SNAP-KG's projector to serve both homophilous and heterophilous KGs.
