Cross-Graph Representation Learning for Unsupervised Graph Alignment

As a crucial prerequisite for graph mining, graph alignment aims to find node correspondences across multiple correlated graphs. The main difficulty of graph alignment lies in how to seamlessly bridge multiple graphs with distinct topology structures and attribute distributions. A vast majority of earlier efforts tackle this problem based on alignment consistency, which directly measures the attribute and structure similarity of nodes. However, alignment consistency is prone to be violated due to the radically different patterns owned by different graphs. Another group of methods tackle the problem in a supervised manner by learning a mapping function that maps the node representations of both the source and target graphs into the same feature space. However, these methods heavily rely on observed anchor links between different graphs while these anchor links are usually limited or even absent in many real-world applications. To address these issues, we propose an unsupervised cross-graph representation learning framework to jointly learn the node representations of different graphs in a unified deep model. Specifically, we employ an auto-encoder model to learn the cross-graph node representations based on both attribute and structure reconstruction, where source and target graphs share the same encoder but are decoded by their respective decoders. To step further, we also introduce a discriminator to better align the learned representations for different graphs via adversarial training. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed approach.

[1]  Li Liu,et al.  Aligning Users across Social Networks Using Network Embedding , 2016, IJCAI.

[2]  Hanghang Tong,et al.  iNEAT: Incomplete Network Alignment , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[3]  Hanghang Tong,et al.  FINAL: Fast Attributed Network Alignment , 2016, KDD.

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

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

[6]  P. Sasikumar,et al.  K-Means Clustering in Wireless Sensor Networks , 2012, 2012 Fourth International Conference on Computational Intelligence and Communication Networks.

[7]  Tao Zhou,et al.  Link prediction in weighted networks: The role of weak ties , 2010 .

[8]  Zheng Wang,et al.  Active learning for node classification in assortative and disassortative networks , 2011, KDD.

[9]  Philip S. Yu,et al.  COSNET: Connecting Heterogeneous Social Networks with Local and Global Consistency , 2015, KDD.

[10]  Charles Elkan,et al.  Link Prediction via Matrix Factorization , 2011, ECML/PKDD.

[11]  Philip S. Yu,et al.  PCT: Partial Co-Alignment of Social Networks , 2016, WWW.

[12]  Xiaolong Jin,et al.  Predict Anchor Links across Social Networks via an Embedding Approach , 2016, IJCAI.

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

[14]  Chen Wang,et al.  Enhancing Network Embedding with Implicit Clustering , 2019, DASFAA.

[15]  Philip S. Yu,et al.  Multiple Anonymized Social Networks Alignment , 2015, 2015 IEEE International Conference on Data Mining.

[16]  Jun Liu,et al.  Anomaly Detection in Time-Evolving Attributed Networks , 2019, DASFAA.

[17]  Huan Liu,et al.  Unsupervised Streaming Feature Selection in Social Media , 2015, CIKM.

[18]  Ying Wang,et al.  Algorithms for Large, Sparse Network Alignment Problems , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[19]  Lei Liu,et al.  DeepLink: A Deep Learning Approach for User Identity Linkage , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[20]  Philip S. Yu,et al.  DynGraphGAN: Dynamic Graph Embedding via Generative Adversarial Networks , 2019, DASFAA.

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

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

[23]  Philip S. Yu,et al.  Inferring anchor links across multiple heterogeneous social networks , 2013, CIKM.

[24]  William W. Cohen,et al.  A Comparison of String Metrics for Matching Names and Records , 2003 .

[25]  Danai Koutra,et al.  BIG-ALIGN: Fast Bipartite Graph Alignment , 2013, 2013 IEEE 13th International Conference on Data Mining.

[26]  Bonnie Berger,et al.  Pairwise Global Alignment of Protein Interaction Networks by Matching Neighborhood Topology , 2007, RECOMB.

[27]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.

[28]  Mark Heimann,et al.  REGAL: Representation Learning-based Graph Alignment , 2018, CIKM.

[29]  Lakshmish Ramaswamy,et al.  A distributed approach to node clustering in decentralized peer-to-peer networks , 2005, IEEE Transactions on Parallel and Distributed Systems.