arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.08563cs.LGcs.AIcs.IR
收藏

KMF:面向零样本节点分类的知识感知多面表征学习

KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification

University of Science and Technology of China(中国科学技术大学);State Key Laboratory of Cognitive Intelligence, China(中国认知智能国家重点实验室);Fudan University(复旦大学);Tianjin University(天津大学);Meituan-Dianping Group(美团点评集团)

Likang Wu, Junji Jiang, Hongke Zhao, Hao Wang, Defu Lian, Mengdi Zhang, Enhong Chen

AI总结:

针对零样本节点分类中特征与标签语义对齐忽略多面主题的问题,提出知识感知多面框架KMF,利用KG主题重构节点表征并引入几何约束,实验及跨域推荐验证了其有效性与泛化性。

摘要:

近年来,零样本节点分类(Zero-Shot Node Classification,ZNC)已成为图数据分析中一项新兴且关键的任务。该任务旨在预测训练过程中未观测到的未见类节点。现有工作主要利用图神经网络(Graph Neural Networks,GNNs)关联特征原型与标签语义,从而实现从已见类到未见类的知识迁移。然而,以往工作忽略了特征—语义对齐中的多面语义倾向,即一个节点的内容通常涵盖与多个标签语义相关的不同主题。因此,有必要分离并判断那些极大影响认知能力的语义因素,以提升模型的泛化性。为此,本文提出一种知识感知多面框架(Knowledge-Aware Multi-Faceted framework,KMF),通过抽取的基于知识图谱(Knowledge Graph,KG)的主题来增强标签语义的丰富性。随后,每个节点的内容被重构为主题级表征,从而为不同标签提供多面且细粒度的语义相关性。由于图实例(即节点)表征的特殊性,本文提出一种新的几何约束,以缓解由节点信息聚合导致的原型漂移问题。最后,我们在多个公共图数据集上进行了大量实验,并设计了一个零样本跨域推荐应用。定量结果通过与最先进基线方法的比较,证明了KMF的有效性和泛化能力。

英文摘要:

Recently, Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis. This task aims to predict nodes from unseen classes which are unobserved in the training process. Existing work mainly utilizes Graph Neural Networks (GNNs) to associate features' prototypes and labels' semantics thus enabling knowledge transfer from seen to unseen classes. However, the multi-faceted semantic orientation in the feature-semantic alignment has been neglected by previous work, i.e. the content of a node usually covers diverse topics that are relevant to the semantics of multiple labels. It's necessary to separate and judge the semantic factors that tremendously affect the cognitive ability to improve the generality of models. To this end, we propose a Knowledge-Aware Multi-Faceted framework (KMF) that enhances the richness of label semantics via the extracted KG (Knowledge Graph)-based topics. And then the content of each node is reconstructed to a topic-level representation that offers multi-faceted and fine-grained semantic relevancy to different labels. Due to the particularity of the graph's instance (i.e., node) representation, a novel geometric constraint is developed to alleviate the problem of prototype drift caused by node information aggregation. Finally, we conduct extensive experiments on several public graph datasets and design an application of zero-shot cross-domain recommendation. The quantitative results demonstrate both the effectiveness and generalization of KMF with the comparison of state-of-the-art baselines.

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。

↑