面向图神经网络表征学习的类别知识探针
Category-wise knowledge probers for representation learning of graph neural networks
黄兴宇 1赵明宇 2吕子钰1
作者信息
- 1. 中国科学院深圳先进技术研究院,广东 深圳 518055;中山大学网络空间安全学院,广东 深圳 518107
- 2. 中国科学院深圳先进技术研究院,广东 深圳 518055;中国科学院大学,北京 100101
- 折叠
摘要
针对图神经网络(graph neural network,GNN)模型缺乏相应的探针这一问题,提出面向图神经网络表征学习的知识探测框架,基于不同领域数据的类别属性设计 2 种类别感知的知识探针,分别为聚类探针和对比聚类探针.2 种探针分别探测不同模型的表征效果并给出相应的分数.在引用网络、社交网络和生物网络等 3 个邻域的 8 个数据集上,对 7 个经典的图神经网络模型的表征学习实现了系统性地知识探测和评估实验,归纳出探测和评估结论.
Abstract
In order to solve the problem that the graph neural network model lacks corresponding probes,a knowledge detection framework for graph neural network representation learning is proposed,and two kinds of class-aware knowledge probes are designed based on the category attributes of data in different domains,namely clustering probes and contrastive clustering probes.The two probe the characterization effect of different models and give corresponding scores.On 8 datasets in 3 neighborhoods,inclu-ding reference networks,social networks and biological networks,the representation learning of 7 classical graph neural network models realizes systematic knowledge detection and evaluation experiments,and summarizes the detection and evaluation conclu-sions.
关键词
图神经网络/知识探针/模型评价/表征学习Key words
graph neural network/knowledge probing/model evaluation/representation learning引用本文复制引用
基金项目
国家自然科学基金资助项目(62002352)
广东省基础与应用基础研究基金资助项目(2023A1515012848)
出版年
2024
NETL
NSTL
万方数据