MixSp: A Framework for Embedding Heterogeneous Information Networks With Arbitrary Number of Node and Edge Types

Heterogeneous information network (HIN) embedding is to encode network structure into node representations with the heterogeneous semantics of different node and edge types considered. However, since each HIN may have a unique nature, e.g., a unique set of node and edge types, a model designed for one type of networks may not be applicable to or effective on another type. In this article, we thus attempt to propose a framework for HINs with arbitrary number of node and edge types. The proposed framework constructs a novel mixture-split representation of an HIN, and hence is named as MixSp. The mixture sub-representation and the split sub-representation serve as two different views of the network. Compared with existing models which only learn from the original view, MixSp thus may exploit more comprehensive information. Node representations in each view are learned by embedding the respective network structure. Moreover, the node representations are further refined through cross-view co-regularization. The framework is instantiated in three models which differ from each other in the co-regularization. Extensive experiments on three real-world datasets show MixSp outperforms several recent models in both node classification and link prediction tasks even though MixSp is not designed for a particular type of HINs.

[1]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[2]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[3]  Wei Lu,et al.  Deep Neural Networks for Learning Graph Representations , 2016, AAAI.

[4]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[5]  Jiawei Han,et al.  Mining Heterogeneous Information Networks by Exploring the Power of Links , 2009, ALT.

[6]  Philip S. Yu,et al.  BL-MNE: Emerging Heterogeneous Social Network Embedding Through Broad Learning with Aligned Autoencoder , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[7]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[8]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[9]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[10]  Yupeng Gu,et al.  RaRE: Social Rank Regulated Large-scale Network Embedding , 2018, WWW.

[11]  P. Tseng.  Convergence of a Block Coordinate Descent Method for Nondifferentiable Minimization , 2001 .

[12]  Huan Liu,et al.  Discovering Overlapping Groups in Social Media , 2010, 2010 IEEE International Conference on Data Mining.

[13]  Geoff Holmes,et al.  MEKA: A Multi-label/Multi-target Extension to WEKA , 2016, J. Mach. Learn. Res..

[14]  Francesco Bonchi,et al.  Cold start link prediction , 2010, KDD.

[15]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[16]  Philip S. Yu,et al.  Multi-task Network Embedding , 2017, 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[17]  Philip S. Yu,et al.  On Exploring Semantic Meanings of Links for Embedding Social Networks , 2018, WWW.

[18]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[19]  L. Armijo.  Minimization of functions having Lipschitz continuous first partial derivatives. , 1966 .

[20]  Ryan A. Rossi,et al.  Deep Inductive Network Representation Learning , 2018, WWW.

[21]  Zhaochun Ren,et al.  Multi-Dimensional Network Embedding with Hierarchical Structure , 2018, WSDM.

[22]  Philip S. Yu,et al.  ICANE: interaction content-aware network embedding via co-embedding of nodes and edges , 2018, International Journal of Data Science and Analytics.

[23]  Philip S. Yu,et al.  Multi-view Graph Embedding with Hub Detection for Brain Network Analysis , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[24]  Philip S. Yu,et al.  Embedding of Embedding (EOE): Joint Embedding for Coupled Heterogeneous Networks , 2017, WSDM.

[25]  Yizhou Sun,et al.  Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification , 2016, WSDM.

[26]  Jiawei Han,et al.  Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks , 2018, KDD.

[27]  Jiawei Han,et al.  An Attention-based Collaboration Framework for Multi-View Network Representation Learning , 2017, CIKM.

[28]  Huan Liu,et al.  Multi-Layered Network Embedding , 2018, SDM.

[29]  Jure Leskovec,et al.  Image Labeling on a Network: Using Social-Network Metadata for Image Classification , 2012, ECCV.

[30]  Jian Li,et al.  Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec , 2017, WSDM.

[31]  Qiaozhu Mei,et al.  PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks , 2015, KDD.

[32]  Jon M. Kleinberg,et al.  The link-prediction problem for social networks , 2007, J. Assoc. Inf. Sci. Technol..

[33]  Xiao Liu,et al.  Co-Regularized Deep Multi-Network Embedding , 2018, WWW.

[34]  Wang-Chien Lee,et al.  HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning , 2017, CIKM.

[35]  Yanjie Fu,et al.  LATTE: Application Oriented Social Network Embedding , 2017, 2019 IEEE International Conference on Big Data (Big Data).

[36]  Kilian Q. Weinberger,et al.  Large Margin Multi-Task Metric Learning , 2010, NIPS.

[37]  Philip S. Yu,et al.  Network Embedding via Coupled Kernelized Multi-Dimensional Array Factorization , 2020, IEEE Transactions on Knowledge and Data Engineering.

[38]  Jiawei Han,et al.  mvn2vec: Preservation and Collaboration in Multi-View Network Embedding , 2018, ArXiv.

[39]  Xiaochun Cao,et al.  Diversity-induced Multi-view Subspace Clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[41]  Qiongkai Xu,et al.  GraRep: Learning Graph Representations with Global Structural Information , 2015, CIKM.

[42]  Philip S. Yu,et al.  Cross View Link Prediction by Learning Noise-resilient Representation Consensus , 2017, WWW.

[43]  Xuelong Li,et al.  Parameter-Free Auto-Weighted Multiple Graph Learning: A Framework for Multiview Clustering and Semi-Supervised Classification , 2016, IJCAI.

[44]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.

[45]  Vasant Honavar,et al.  Multi-view Network Embedding via Graph Factorization Clustering and Co-regularized Multi-view Agreement , 2018, 2018 IEEE International Conference on Data Mining Workshops (ICDMW).

[46]  Jian Pei,et al.  Community Preserving Network Embedding , 2017, AAAI.

[47]  Philip S. Yu,et al.  Multiple Social Role Embedding , 2017, 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[48]  Mark E. J. Newman,et al.  The Structure and Function of Complex Networks , 2003, SIAM Rev..

[49]  Jie Tang,et al.  ArnetMiner: extraction and mining of academic social networks , 2008, KDD.

[50]  Jiawei Han,et al.  AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks , 2018, SDM.

[51]  Charu C. Aggarwal,et al.  Heterogeneous Network Embedding via Deep Architectures , 2015, KDD.

[52]  Minyi Guo,et al.  GraphGAN: Graph Representation Learning with Generative Adversarial Nets , 2017, AAAI.

[53]  Deli Zhao,et al.  Network Representation Learning with Rich Text Information , 2015, IJCAI.

[54]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.