7-2 开放环境下图神经网络及其应用.pdf

1、石川 教授北京邮电大学开放环境下图神经开放环境下图神经网络与应用网络与应用 2009BUPT TSEG 2网网络建模络建模络是描述和建模复杂系统的通语2融络社交络神经元络信息络物络互联ABC3网网络表示学习络表示学习络表学习成嵌将节点嵌到低维向量空间中应节点分类链路预测社区发现络演化p 易于并p 可结合经典机器学习法4浅浅层模型层模型浅层模型 基于分解的法 e.g.,Laplacian eigenmaps 基于随机游的法 e.g.,DeepWalk,node2vec5深深层模型层模型5深层模型应深层神经络基于动编码器的法 e.g.,DNGR and SDNE基于图神经络的法 聚合邻居信息，并应

2、神经络 e.g.,GCN,GraphSage,GAT6图神经网络图神经网络3.迭代 次:#(%)*#%+*+-/%+*?/#,4.预测:7=softmax(B+*)1.输图 和节点属性 2.初始化:#(E)=E#,7开放开放环境下的图神经网络环境下的图神经网络异质性多种类型节点和边共存动态性图结构和属性动态演化稀疏性可见的交互和属性稀疏脆弱性图结构和属性易受攻击简单静态图难以建模开放环境中的复杂系统8报告内容报告内容 开放环境下图神经络异质图神经络 HAN(HAN2019)动态图神经络 MetaDyGNN(WSDM2022)稀疏图神经络 HeCo(KDD2021)对抗图神经络 RoHe(AAA

3、I2022)l应用9HeterogeneousGraphlHeterogeneous Graph(HG,Heterogeneous Information Network)contain multiple object types and/or multiple link types.Bibliographic dataMovie dataSocial network dataKnowledge graph10Basic Concepts in HGlNetwork schemaMeta-level description of a networklMeta path(Sun VLDB2011

4、)A relation sequences connecting object pairsContain rich semanticsYizhou Sun,Jiawei Han,Xifeng Yan,Philip S.Yu,Tianyi Wu.PathSim:Meta Path-Based Top-k SimilaritySearch in Heterogeneous Information Networks.VLDBpp.992-1003,2011.11Essence of HeterogeneousGraphlA modeling paradigmlA data form=,=,Stati

5、c,Topology,Homogeneous GraphDynamic,Attribute,Heterogeneous GraphGraphSimple,TopologyKnowledge GraphComplex,KnowledgeHeterogeneous GraphControllable complex,Rich semantics12HG RepresentationWhy HG representation Heterogeneity is ubiquitous Information loss Rich semanticsChallenges How to handle hete

6、rogeneity How to fuse information How to capture rich semanticsStatic,TopologyHomogeneous GraphDynamic,AttributedHeterogeneous Graph13Heterogeneous information network Embedding for Recommendation(HERec)Framework of HERecChuan Shi,Binbin Hu,Wayne Xin Zhao,Philip S.Yu.Heterogeneous Information Networ