基于多層特征融合與增強(qiáng)的對(duì)比圖聚類(lèi)

打開(kāi)文本圖片集

Contrastive graph clustering based on multi-level feature fusion andenhancement

Li Zhiming τ1a，1b，1c，2 ，Wei Hepinglat，Zhang Guangkangla，You Dianlong ρ，a，lb，lc，2 （1.a.Schloffotionee&Ein，yoatofofareEgigfberoc，eybofor ComputerVirtalhlog&stmIntegationofHbeiProinceYashnUniersityQiangdaHbei，hina;.S search Institute ofYanshan University，Yanshan University，Shenzhen Guangdong 518o63，China）

Abstract：The majorityofexisting contrastivegraph clustering algorithmsfacethe following issues：theyignorethelow-level featuresand structural informationextracted byshalownetworkswhen generatingnoderepresentation.Thealgorithms neither fullutilizehighorderneighbornodeinformationnorintegrateconfidenceinformationwithtopologicalstructureinformationto construct positive sample pairs.Toaddress theabove issues，thispaper proposed acontrastive graph clustering algorithmbased onmulti-evelfeaturefusionandenhancement.Tealgorithmfirstlyintegratednodefeaturesextractedfromdiferentnetwork layerstoenrichthelow-levelstructural informationofodes.Itthenaggegatednodeinformationthroughthelocaltopolgical correlationsandglobalsemanticsimilaritiesbetweennodestoenhancethecontextualconstraintconsistencyofnoderepresentations.Finaly，combiningconfidenceinformationandtopologicalstructureinformation，thealgorithmconstructedmoreig quality positivesamplepairs to improvetheconsistencyof intra-clusterrepresentation.Theexperimental results showthat CGCMFFEhas excelent performance on four widelyused clustering evaluation metrics.Theoretical analysis and experimental studyunderscoretherucialroleoflow-levelodefeatures，hig-orderneighbornodeinformation，confidence，andtopological structure information in the CGCMFFE algorithm，providing evidence for its superiority.

Key words：multi-level feature fusion；contrastive graph clustering；unsupervised learning

0 引言

深度圖聚類(lèi)是一種利用深度學(xué)習(xí)將圖中節(jié)點(diǎn)數(shù)據(jù)映射到低維稠密向量空間，并以無(wú)監(jiān)督的方式將節(jié)點(diǎn)表示劃分為若干個(gè)不相交簇的技術(shù)[1]。（剩余14750字）