Feature-Dependent Graph Convolutional Autoencoders with Adversarial Training Methods

Graphs are ubiquitous for describing and modeling complicated data structures, and graph embedding is an effective solution to learn a mapping from a graph to a low-dimensional vector space while preserving relevant graph characteristics. Most existing graph embedding approaches either embed the topological information and node features separately or learn one regularized embedding with both sources of information, however, they mostly overlook the interdependency between structural characteristics and node features when processing the graph data into the models. Moreover, existing methods only reconstruct the structural characteristics, which are unable to fully leverage the interaction between the topology and the features associated with its nodes during the encoding-decoding procedure. To address the problem, we propose a framework using autoencoder for graph embedding (GED) and its variational version (VEGD). The contribution of our work is two-fold: 1) the proposed frameworks exploit a feature-dependent graph matrix (FGM) to naturally merge the structural characteristics and node features according to their interdependency; and 2) the Graph Convolutional Network (GCN) decoder of the proposed framework reconstructs both structural characteristics and node features, which naturally possesses the interaction between these two sources of information while learning the embedding. We conducted the experiments on three real-world graph datasets such as Cora, Citeseer and PubMed to evaluate our framework and algorithms, and the results outperform baseline methods on both link prediction and graph clustering tasks.

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

[2]  Chun Wang,et al.  MGAE: Marginalized Graph Autoencoder for Graph Clustering , 2017, CIKM.

[3]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[4]  Max Welling,et al.  Variational Graph Auto-Encoders , 2016, ArXiv.

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

[6]  Dan Wang,et al.  Adversarial Network Embedding , 2017, AAAI.

[7]  David M. Blei,et al.  Relational Topic Models for Document Networks , 2009, AISTATS.

[8]  Philip S. Yu,et al.  Joint Structure Feature Exploration and Regularization for Multi-Task Graph Classification , 2016, IEEE Transactions on Knowledge and Data Engineering.

[9]  Huan Liu,et al.  Leveraging social media networks for classification , 2011, Data Mining and Knowledge Discovery.

[10]  Lina Yao,et al.  Adversarially Regularized Graph Autoencoder , 2018, IJCAI.

[11]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[12]  Enhong Chen,et al.  Learning Deep Representations for Graph Clustering , 2014, AAAI.

[13]  Jian Pei,et al.  A Survey on Network Embedding , 2017, IEEE Transactions on Knowledge and Data Engineering.

[14]  Chengqi Zhang,et al.  Network Representation Learning: A Survey , 2017, IEEE Transactions on Big Data.

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

[16]  Wenjie Li,et al.  Predictive Network Representation Learning for Link Prediction , 2017, SIGIR.

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

[18]  Chengqi Zhang,et al.  Tri-Party Deep Network Representation , 2016, IJCAI.

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

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

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

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

[23]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[24]  Kevin Chen-Chuan Chang,et al.  A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications , 2017, IEEE Transactions on Knowledge and Data Engineering.

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

[26]  Lei Du,et al.  Robust Multi-View Spectral Clustering via Low-Rank and Sparse Decomposition , 2014, AAAI.

[27]  Jian Pei,et al.  Asymmetric Transitivity Preserving Graph Embedding , 2016, KDD.

[28]  Chengqi Zhang,et al.  User Profile Preserving Social Network Embedding , 2017, IJCAI.

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