基于深度学习的异质信息网络表示学习方法综述

doi:10.11896/jsjkx.220800112

Abstract

Abstract: Things in the nature connect mutually.There are various associations between them in the real world.For example,social networks can be constructed by the user-user relationships.The article-author relationship can be used to construct a citation network.In homogeneous networks,nodes or edges are all in the same type,resulting in a lot of information loss.In order to ensure the integrity and richness of information to a greater extent,researchers have proposed heterogeneous information network(HIN),a network model containing multiple types of nodes or edges.By embedding the topological structure and semantic information of HIN into a low-dimensional vector space,downstream tasks can utilize the rich information in the HIN for machine learning or data mining.This paperfocuses on the HIN-based representation learning tasks,and summarizes the recent representation learning methods of HIN which are based on deep learning models.We focus on two main issues:semantics extraction of HIN and information preserving of dynamic HIN.We also illustrate some new applications of HIN-based representation learning,and propose the future development trend of heterogeneous information networks.

Key words: Heterogeneous information networks, Deep learning, Representation learning, Graph neural network, Meta-path

CLC Number:

TP391.3

WANG Huiyan, YU Minghe, YU Ge. Deep Learning-based Heterogeneous Information Network Representation:A Survey[J].Computer Science, 2023, 50(5): 103-114.

References

[1]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.2013:3111-3119.
[2]HAMILTON W L,YING R,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems(NeurIPS).2017:1025-1035.
[3]WANG D,CUI P,ZHU W.Structural Deep Network Embed-ding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:1225-1234.
[4]ZENG X,ZHU S,LU W,et al.Target identification amongknown drugs by deep learning from heterogeneous networks[J].Chemical Science,2020,11(7):1775-1797.
[5]ATHANASIOS T,STJIN V D,ANTON J E,et al.Network visualization and analysis of gene expression data using biolayout express(3D)[J].Nature Protocols,2009,4(10):1535-1550.
[6]YANG X,WANG W,MA J L,et al.BioNet:a large-scale and heterogeneous biological network model for interaction prediction with graph convolution[J].Briefings in Bioinformatics,2022,23(1):bbab491.
[7]GAO Y L,LI X Y,HAO P,et al.HinCTI:A Cyber Threat Intelligence Modeling and Identification System Based on Heterogeneous Information Network[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(2):708-722.
[8]HOU S,YE Y,SONG Y,et al.HinDroid:An Intelligent Android Malware Detection System Based on Structured Heterogeneous Information Network[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:1507-1515.
[9]WU S Q,DONG Y H,WANG X,et al.Learning attribute net-work algorithm based on high-order similarity[J].Telecommunication Science,2020,36(12):13.
[10]ZHANG J,SHI X,ZHAO S,et al.STAR-GCN:stacked and reconstructed graph convolutional networks for recommender systems[C]//Proceedings of the 28th International Joint Confe-rence on Artificial Intelligence.2019:4264-4270.
[11]GONG J,WANG S,WANG J,et al.Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:79-88.
[12]CHEN C,MA W,ZHANG M,et al.Graph HeterogeneousMulti-Relational Recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:3959-3966.
[13]LU Y,FANG Y,SHI C.Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation[C]//Procee-dings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:1563-1573.
[14]WANG X,LU Y,SHI C,et al.Dynamic Heterogeneous Information Network Embedding with Meta-path based Proximity[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(3):1117-1132.
[15]ZHANG Y,XIONG Y,KONG X,et al.Deep Collective Classifi-cation in Heterogeneous Information Networks[C]//Procee-dings of the 2018 World Wide Web Conference.2018:399-408.
[16]LIU M,LIU J,CHEN Y,et al.AHNG:Representation Learning on Attributed Heterogeneous Network[J].Information Fusion,2019,50:221-230.
[17]XU S,YANG C,SHI C,et al.Topic-aware HeterogeneousGraph Neural Network for Link Prediction[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:2261-2270.
[18]WANG H,ZHANG F,HOU M,et al.SHINE:Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction[C]//Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining.2018:592-600.
[19]SHI C,WANG R J,WANG X.Survey on Heterogeneous Information Networks[J].Journal of Software,2022,33(2):598-621.
[20]ZHOU L H,WANG J L,WANG L Z.HeterogeneousInformationNetworkRepresentationLearning:ASurvey[J].Chinese Journal of Computers,2022,45(1):160-189.
[21]WANG X,BO D,SHI C,et al.A Survey on HeterogeneousGraph Embedding:Methods,Techniques,Applications and Sources[J].IEEE Transactions on Big Data,2023,9(2):415-436.
[22]LIU J W,SHI C,YANG C,et al.Heterogeneous Information Network based Recommender Systems:a survey[J].Journal of Cyber Security,2021,6(5):1-16.
[23]SUN Y,HAN J.Mining heterogeneous information networks:a structural analysis approach[J].SIGKDD Explor Newsl,2013,14(2):20-28.
[24]HUANG Z,ZHENG Y,CHENG R,et al.Meta Structure:Computing Relevance in Large Heterogeneous Information Networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:1595-1604.
[25]ZHANG Z,HUANG J,TAN Q,et al.CMG2Vec:A composite meta-graph based heterogeneous information network embedding approach[J].Knowledge-Based Systems,2021,216:106661.1-106661.14.
[26]PEROZZI B,AL-RFOU R,SKIENA S.DeepWalk:online lear-ning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.2014:701-710.
[27]JIANG H,SONG Y,WANG C,et al.Semi-supervised learning over heterogeneous information networks by ensemble of meta-graph guided random walks[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.2017:1944-1950.
[28]GAO X,CHEN J,ZHAN Z,et al.Learning heterogeneous information network embeddings via relational triplet network[J].Neurocomputing,2020,412:31-41.
[29]XU L,WEI X,CAO J,et al.Embedding of Embedding(EOE):Joint Embedding for Coupled Heterogeneous Networks[C]//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.2017:741-749.
[30]TANG J,QU M,MEI Q.PTE:Predictive Text Embeddingthrough Large-scale Heterogeneous Text Networks[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2015:1165-1174.
[31]SCARSELLI F,GORI M,TSOI A C,et al.The Graph Neural Network Model[J].IEEE Transactions on Neural Networks,2009,20(1):61-80.
[32]LI X,WEN L,QIAN C,et al.GAHNE:Graph-Aggregated He-terogeneous Network Embedding[C]//proceedings of the 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence(ICTAI).2020:1012-1019.
[33]ZHU Z,FAN X,CHU X,et al.HGCN:A Heterogeneous Graph Convolutional Network-Based Deep Learning Model Toward Collective Classification[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:1161-1171.
[34]YAN D,XIE W,ZHANG Y.Heterogeneous information net-work-based interest composition with graph neural network for recommendation[J].Applied Intelligence,2022,52(10):11199-11213.
[35]ZHAO J,WANG X,SHI C,et al.Heterogeneous Graph Structure Learning for Graph Neural Networks[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence.2021,35:4697-4705.
[36]QIN X,SHEIKH N,REINWALD B,et al.Relation-awareGraph Attention Model with Adaptive Self-adversarial Training[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence.2021:9368-9376.
[37]WANG Y,DUAN Z,LIAO B,et al.Heterogeneous Attributed Network Embedding with Graph Convolutional Networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:10061-10062.
[38]ZHAO J,LIU X,YAN Q,et al.Multi-attributed heterogeneous graph convolutional network for bot detection[J].Information Sciences,2020,537:380-393.
[39]FU X,ZHANG J,MENG Z,et al.MAGNN:Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding[C]//Proceedings of The Web Conference(WWW).2020:2331-2341.
[40]TANG S,LEI Y,WANG S.DisenHAN:Disentangled Heterogeneous Graph Attention Network for Recommendation[C]//The 29th ACM International Conference on Information and Knowledge Management(CIKM '20).2020.
[41]CEN Y,ZOU X,ZHANG J,et al.Representation Learning for Attributed Multiplex Heterogeneous Network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Know-ledge Discovery & amp;Data Mining.2019:1358-1368.
[42]WANG X,LIU N,HAN H,et al.Self-supervised Heteroge-neous Graph Neural Network with Co-contrastive Learning[C]//Proceedings of the 27th ACM SIGKDD Conference on Know-ledge Discovery & Data Mining.2021:1726-1736.
[43]WANG H W,WANG J,WANG J L,et al.GraphGAN:GraphRepresentation Learning with Generative Adversarial Nets[C]//Proceedings of the AAAI Conferenceon Artificial Intelligence.2018:2508-2515.
[44]HONG H,LI X,WANG M.GANE:A Generative Adversarial Network Embedding[J].IEEE Transactions on Neural Networks and Learning Systems,2020,31(7):2325-2335.
[45]ZHANG C,WANG Y,ZHU L,et al.Multi-Graph Heteroge-neous Interaction Fusion for Social Recommendation[J].ACM Transactions Information Systems,2022,40(2):28:21-28:26.
[46]WANG R J,SHI C,ZHAO T Y,et al.Heterogeneous Information Network Embedding with Adversarial Disentangler[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(2):1581-1593.
[47]HOU S,FAN Y,JU M,et al.Disentangled RepresentationLearning in Heterogeneous Information Network for Large-scale Android Malware Detection in the COVID-19 Era and Beyond[C]//the 35th AAAI Conference on Artificial Intelligence.2021:7754-7761.
[48]ZHAO K,BAI T,WU B,et al.Deep Adversarial Completion for Sparse Heterogeneous Information Network Embedding[C]//Proceedings of The Web Conference(WWW).2020:508-518.
[49]HINTON G E,ZEMEL R S.Autoencoders,minimum description length and Helmholtz free energy[C]//Proceedings of the 6th International Conference on Neural Information Processing Systems.1993:3-10.
[50]YU B,HU J,XIE Y,et al.Rich heterogeneous information preserving network representation learning[J].Pattern Recognit,2020,108:107564.
[51]ZHANG C,WANG G,YU B,et al.Proximity-aware heterogeneous information network embedding[J].Knowledge-Based Systems,2020,193:105468.1-105468.13.
[52]ZHU Z,FAN X,CHU X,et al.LRHNE:A Latent-Relation Enhanced Embedding Method for Heterogeneous Information Networks[C]//Proceedings of the 29th ACM International Confe-rence on Information & Knowledge Management.2020:1923-1932.
[53]ZHENG J,MA Q,GU H,et al.Multi-view Denoising GraphAuto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2021:2338-2348.
[54]XIE F,ZHENG A,CHEN L,et al.Attentive Meta-graph Embedding for item Recommendation in heterogeneous information networks-ScienceDirect[J].Knowledge-Based Systems,2020,211:106524.1-106524.13.
[55]ZHANG X,CHEN L.mSHINE:A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(7):3391-3404.
[56]YANG Y,GUAN Z,LI J,et al.Interpretable and Efficient Hete-rogeneous Graph Convolutional Network[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(2):1637-1650.
[57]CHANG Y,CHEN C,HU W,et al.Megnn:Meta-path extracted graph neural network for heterogeneous graph representation learning[J].Knowledge-Based Systems,2022,235:107611.1-107611.11.
[58]HWANG D,PARK J,KWON S,et al.Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs[C]//Advances in Neural Information Processing Systems(NeurIPS).2020:10294-10305.
[59]CHAIRATANAKUL N,LIU X,MURATA T.PGRA:Projected graph relation-feature attention network for heterogeneous information network embedding[J].Information Sciences,2021,570(1):769-794.
[60]HONG H,GUO H,LIN Y,et al.An Attention-based GraphNeural Network for Heterogeneous Structural Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:4132-4139.
[61]PENG H,YANG R,WANG Z,et al.LIME:Low-Cost and Incremental Learning for Dynamic Heterogeneous Information Networks[J].IEEE Transactions on Computers,2022,71(3):628-642.
[62]JIANG S,KOCH B,SUN Y.HINTS:Citation Time Series Prediction for New Publications via Dynamic Heterogeneous Information Network Embedding[C]//Proceedings of the Web Conference(WWW).2021:3158-3167.
[63]ZHANG Z,HUANG J,TAN Q.Multi-view Dynamic Heterogeneous Information Network Embedding[J].The Computer Journal,2022,65(8):2016-2033.
[64]XIE Y,OU Z,CHEN L,et al.Learning and Updating Node Embedding on Dynamic Heterogeneous Information Network[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining(WSDM).2021:184-192.
[65]HUANG H,SHI R,ZHOU W,et al.Temporal Heterogeneous Information Network Embedding[C]//Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence.2021:1470-1476.
[66]HONG H,LIN Y,YANG X,et al.HetETA:Heterogeneous Information Network Embedding for Estimating Time of Arrival[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:2444-2454.
[67]LUO W,ZHANG H,YANG X,et al.Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:3213-3223.
[68]GUO Z W,TANG L G,GUO T,et al.Deep Graph neural network-based spammer detection under the perspective of heterogeneous cyberspace[J].Future Generation Computer Systems,2021,117:205-218.
[69]SUN X,YIN H,LIU B,et al.Heterogeneous Hypergraph Embedding for Graph Classification[C]//proceedings of the Proceedings of the 14th ACM International Conference on Web Search and Data Mining(WSDM).2021:725-733.
[70]SHEHNEPOOR S,TOGNERI R,LIU W,et al.HIN-RNN:A Graph Representation Learning Neural Network for Fraudster Group Detection With No Handcrafted Features[J].arXiv:2015.11602,2021.
[71]LIU Z,DOU Y,YU P S,et al.Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:1569-1572.
[72]ZHONG Q,LIU Y,AO X,et al.Financial Defaulter Detection on Online Credit Payment via Multi-view Attributed Heterogeneous Information Network[C]//Proceedings of The Web Conference(WWW).2020:785-795.
[73]HU B,ZHANG Z,SHI C,et al.Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hie-rarchical Attention Mechanism[C]//Proceedings of the THIRTY-THIRD AAAI Conference on Artificial Intelligence.2019:946-953.
[74]JIA R,CAO Y,TANG H,et al.Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network[C]//proceedings of the Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).2020:3622-3631.
[75]XU R,LIU T,LI L,et al.Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker[C]//Annual Meeting of the Association for Computational Linguistics.2021:3533-3546.
[76]WU Y,ZHAO S,GUO R.A novel community answer matching approach based on phrase fusion heterogeneous information network[J].Information Processing & Management,2021,58(1):102408.
[77]SUN Q,PENG H,LI J,et al.Pairwise Learning for NameDisambiguation in Large-Scale Heterogeneous Academic Networks[C]//Proceedings of the 2020 IEEE International Conference on Data Mining(ICDM).2020:511-520.
[78]WANG H,WANG R,WEN C,et al.Author Name Disambi-guation on Heterogeneous Information Network with AdversarialRepresentation Learning[C]//THIRTY-FOURTH AAAI Conference on Artificial Intelligence.2020:238-235.
[79]TANG J,LOU T,KLEINBERG J,et al.Transfer Learning to Infer Social Ties across Heterogeneous Networks[J].ACM Transactions on Information System,2016,34(2):1-43.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Deep Learning-based Heterogeneous Information Network Representation:A Survey

PDF (PC)

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0

[1]	HAN Junling, LI Bo, KANG Xiaodong, YANG Jingyi, LIU Hanqing, WANG Xiaotian. Cardiac MRI Image Segmentation Based on Faster R-CNN and U-net [J]. Computer Science, 2023, 50(6A): 220600047-9.
[2]	LIU Haowei, YAO Jingchi, LIU Bo, BI Xiuli, XIAO Bin. Two-stage Method for Restoration of Heritage Images Based on Muti-scale Attention Mechanism [J]. Computer Science, 2023, 50(6A): 220600129-8.
[3]	LI Fan, JIA Dongli, YAO Yumin, TU Jun. Graph Neural Network Few Shot Image Classification Network Based on Residual and Self-attention Mechanism [J]. Computer Science, 2023, 50(6A): 220500104-5.
[4]	XIE Puxuan, CUI Jinrong, ZHAO Min. Electiric Bike Helment Wearing Detection Alogrithm Based on Improved YOLOv5 [J]. Computer Science, 2023, 50(6A): 220500005-6.
[5]	WAN Haibo, JIANG Lei, WANG Xiao. Real-time Detection of Motorcycle Lanes Based on Deep Learning [J]. Computer Science, 2023, 50(6A): 220200066-5.
[6]	WANG Xiaotian, LI Bo, KANG Xiaodong, LIU Hanqing, HAN Junling, YANG Jingyi. Study on Phased Target Detection in CT Image [J]. Computer Science, 2023, 50(6A): 220200063-10.
[7]	YU Jiabao, YAO Junmei, XIE Ruitao, WU Kaishun, MA Junchao. Tag Identification for UHF RFID Systems Based on Deep Learning [J]. Computer Science, 2023, 50(6A): 220200151-6.
[8]	GAO Xiang, TANG Jiqiang, ZHU Junwu, LIANG Mingxuan, LI Yang. Study on Named Entity Recognition Method Based on Knowledge Graph Enhancement [J]. Computer Science, 2023, 50(6A): 220700153-6.
[9]	ZENG Wu, MAO Guojun. Few-shot Learning Method Based on Multi-graph Feature Aggregation [J]. Computer Science, 2023, 50(6A): 220400029-10.
[10]	HOU Yanrong, LIU Ruixia, SHU Minglei, CHEN Changfang, SHAN Ke. Review of Research on Denoising Algorithms of ECG Signal [J]. Computer Science, 2023, 50(6A): 220300094-11.
[11]	GU Yuhang, HAO Jie, CHEN Bing. Semi-supervised Semantic Segmentation for High-resolution Remote Sensing Images Based on DataFusion [J]. Computer Science, 2023, 50(6A): 220500001-6.
[12]	LIANG Mingxuan, WANG Shi, ZHU Junwu, LI Yang, GAO Xiang, JIAO Zhixiang. Survey of Knowledge-enhanced Natural Language Generation Research [J]. Computer Science, 2023, 50(6A): 220200120-8.
[13]	WANG Dongli, YANG Shan, OUYANG Wanli, LI Baopu, ZHOU Yan. Explainability of Artificial Intelligence:Development and Application [J]. Computer Science, 2023, 50(6A): 220600212-7.
[14]	GAO Xiang, WANG Shi, ZHU Junwu, LIANG Mingxuan, LI Yang, JIAO Zhixiang. Overview of Named Entity Recognition Tasks [J]. Computer Science, 2023, 50(6A): 220200119-8.
[15]	LI Yang, WANG Shi, ZHU Junwu, LIANG Mingxuan, GAO Xiang, JIAO Zhixiang. Summarization of Aspect-level Sentiment Analysis [J]. Computer Science, 2023, 50(6A): 220400077-7.