GraphInception: Convolutional Neural Networks for Collective Classification in Heterogeneous Information Networks

Collective classification has attracted considerable attention, where the labels within a group of instances are correlated and should be inferred collectively. Conventional approaches on collective classification mainly focus on exploiting simple relational features. However, many applications involve complex dependencies among the instances, which are obscure/hidden in the networks. To capture these dependencies, we need to go beyond simple relational features and extract deep dependencies between the instances. In this paper, we study the problem of deep collective classification in Heterogeneous Information Networks(HINs). Different from conventional autocorrelations, which are given explicitly by the links in the network, complex autocorrelations are obscure/hidden in HINs, and should be inferred from existing links in a hierarchical order. This problem is highly challenging due to multiple types of dependencies among the nodes and complexity of the relational features. We proposed a deep convolutional collective classification method, called GraphInception, to learn the deep relational features in HINs. And we presented two versions of the models with different inference styles. The proposed methods can automatically generate a hierarchy of relational features with different complexities. Extensive experiments on real-world networks demonstrate that our approach can improve the collective classification performance by considering deep relational features in HINs.

[1]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

[2]  Sepandar D. Kamvar,et al.  An Analytical Comparison of Approaches to Personalizing PageRank , 2003 .

[3]  Nitzan Guberman,et al.  On Complex Valued Convolutional Neural Networks , 2016, ArXiv.

[4]  David D. Jensen,et al.  Why Stacked Models Perform Effective Collective Classification , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[5]  Aditya K. Ghose,et al.  Predicting Delays in Software Projects Using Networked Classification (T) , 2015, 2015 30th IEEE/ACM International Conference on Automated Software Engineering (ASE).

[6]  Wolfgang Gatterbauer,et al.  Semi-Supervised Learning with Heterophily , 2014, ArXiv.

[7]  Bin Chen,et al.  Assessing Drug Target Association Using Semantic Linked Data , 2012, PLoS Comput. Biol..

[8]  Philip S. Yu,et al.  Meta path-based collective classification in heterogeneous information networks , 2012, CIKM.

[9]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[10]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[11]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[12]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[13]  M. Narasimha Murty,et al.  Structural Neighborhood Based Classification of Nodes in a Network , 2016, KDD.

[14]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Danai Koutra,et al.  Linearized and Single-Pass Belief Propagation , 2014, Proc. VLDB Endow..

[16]  Jennifer Neville,et al.  Iterative Classification in Relational Data , 2000 .

[17]  Adam Coates,et al.  Deep Learning for Machine Vision , 2013, BMVC.

[18]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[19]  Jiawei Han,et al.  Ranking-based classification of heterogeneous information networks , 2011, KDD.

[20]  Corrado Loglisci,et al.  Collective regression for handling autocorrelation of network data in a transductive setting , 2015, Journal of Intelligent Information Systems.

[21]  William W. Cohen,et al.  Stacked Graphical Models for Efficient Inference in Markov Random Fields , 2007, SDM.

[22]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[23]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[24]  Philip S. Yu,et al.  Multi-label classification by mining label and instance correlations from heterogeneous information networks , 2013, KDD.

[25]  Xavier Bresson,et al.  Structured Sequence Modeling with Graph Convolutional Recurrent Networks , 2016, ICONIP.

[26]  Reynold Cheng,et al.  Discovering Meta-Paths in Large Heterogeneous Information Networks , 2015, WWW.

[27]  Xianghua Xie,et al.  Graph Based Convolutional Neural Network , 2016, ArXiv.

[28]  David W. Aha,et al.  Labels or attributes?: rethinking the neighbors for collective classification in sparsely-labeled networks , 2013, CIKM.

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

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

[31]  Svetha Venkatesh,et al.  Column Networks for Collective Classification , 2016, AAAI.

[32]  Jennifer Neville,et al.  Combining Gradient Boosting Machines with Collective Inference to Predict Continuous Values , 2016, ArXiv.

[33]  Jürgen Schmidhuber,et al.  Highway Networks , 2015, ArXiv.

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

[35]  Yizhou Sun,et al.  Graph Regularized Transductive Classification on Heterogeneous Information Networks , 2010, ECML/PKDD.

[36]  Ryan A. Rossi,et al.  Relational Similarity Machines (RSM): A Similarity-based Learning Framework for Graphs , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[37]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing, 2nd Edition , 1999 .

[38]  Yoshua Bengio,et al.  Deep Learning for NLP (without Magic) , 2012, ACL.

[39]  L. Getoor,et al.  Link-Based Classification , 2003, Encyclopedia of Machine Learning and Data Mining.

[40]  Yizhou Sun,et al.  Mining Heterogeneous Information Networks: Principles and Methodologies , 2012, Mining Heterogeneous Information Networks: Principles and Methodologies.

[41]  Yangyong Zhu,et al.  NetCycle: Collective Evolution Inference in Heterogeneous Information Networks , 2016, KDD.

[42]  Christos Faloutsos,et al.  Fast Random Walk with Restart and Its Applications , 2006, Sixth International Conference on Data Mining (ICDM'06).

[43]  Jennifer Neville,et al.  Deep Collective Inference , 2017, AAAI.

[44]  Yanfang Ye,et al.  Heterogeneous Graph Attention Network , 2019, WWW.

[45]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[46]  Jennifer Neville,et al.  Why collective inference improves relational classification , 2004, KDD.