Epidemic Graph Convolutional Network

A growing trend recently is to harness the structure of today's big data, where much of the data can be represented as graphs. Simultaneously, graph convolutional networks (GCNs) have been proposed and since seen rapid development. More recently, due to the scalability issues that arise when attempting to utilize these powerful models on real-world data, methodologies have sought the use of sampling techniques. More specifically, minibatches of nodes are formed and then sets of nodes are sampled to aggregate from in one or more layers. Among these methods, the two prominent ways are based on sampling nodes from either a local or global perspective. In this work, we first observe the similarities in the two sampling strategies to that of epidemic and diffusion network models. Then we harness this understanding to fuse together the benefits of sampling from both a local and global perspective while alleviating some of the inherent issues found in both through the use of a low-dimensional approximation for the path-based Katz similarity measure. Our proposed framework, Epidemic Graph Convolutional Network (EGCN), is thus able to achieve improved performance over sampling from just one of the two perspectives alone. Empirical experiments are performed on several public benchmark datasets to verify the effectiveness over existing methodologies for the node classification task and we furthermore present some empirical parameter analysis of EGCN.

[1]  Hector Garcia-Molina,et al.  Combating Web Spam with TrustRank , 2004, VLDB.

[2]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

[3]  Jiliang Tang,et al.  Adversarial Attacks and Defenses in Images, Graphs and Text: A Review , 2019, International Journal of Automation and Computing.

[4]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[5]  Jiliang Tang,et al.  Signed Graph Convolutional Networks , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

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

[7]  KleinbergJon,et al.  The link-prediction problem for social networks , 2007 .

[8]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017, 1705.08415.

[9]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[10]  Graeme C. Wake,et al.  Lyapunov functions and global stability for SIR, SIRS, and SIS epidemiological models , 2002, Appl. Math. Lett..

[11]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[12]  Jon Kleinberg,et al.  The link prediction problem for social networks , 2003, CIKM '03.

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

[14]  Leo Katz,et al.  A new status index derived from sociometric analysis , 1953 .

[15]  Tao Zhou,et al.  Immunization of susceptible–infected model on scale-free networks , 2006, physics/0610138.

[16]  Stephan Gunnemann,et al.  Certifiable Robustness and Robust Training for Graph Convolutional Networks , 2019, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.

[17]  Cao Xiao,et al.  FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling , 2018, ICLR.

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Le Song,et al.  Adversarial Attack on Graph Structured Data , 2018, ICML.

[20]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[21]  Junzhou Huang,et al.  Adaptive Sampling Towards Fast Graph Representation Learning , 2018, NeurIPS.

[22]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[23]  Suhang Wang,et al.  Attacking Graph Convolutional Networks via Rewiring , 2019, ArXiv.

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

[25]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017 .

[26]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[27]  Samy Bengio,et al.  Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks , 2019, KDD.

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

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

[30]  P. Bonacich.  Factoring and weighting approaches to status scores and clique identification , 1972 .

[31]  Romualdo Pastor-Satorras,et al.  Nature of the epidemic threshold for the susceptible-infected-susceptible dynamics in networks. , 2013, Physical review letters.

[32]  Tyler Derr.  Relevance Measurements in Online Signed Social Networks , 2018 .

[33]  Meng Wang,et al.  SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation , 2018, ArXiv.

[34]  Pasquale Minervini,et al.  Convolutional 2D Knowledge Graph Embeddings , 2017, AAAI.

[35]  Kevin Chen-Chuan Chang,et al.  Learning Community Embedding with Community Detection and Node Embedding on Graphs , 2017, CIKM.

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

[37]  Jure Leskovec,et al.  Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time , 2017, WWW.

[38]  Jure Leskovec,et al.  Position-aware Graph Neural Networks , 2019, ICML.

[39]  Jennifer Widom,et al.  Scaling personalized web search , 2003, WWW '03.

[40]  Stephan Günnemann,et al.  Adversarial Attacks on Graph Neural Networks via Meta Learning , 2019, ICLR.

[41]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[42]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[43]  Phillip Bonacich,et al.  Some unique properties of eigenvector centrality , 2007, Soc. Networks.

[44]  Wenwu Zhu,et al.  Robust Graph Convolutional Networks Against Adversarial Attacks , 2019, KDD.

[45]  Noah E. Friedkin,et al.  Theoretical Foundations for Centrality Measures , 1991, American Journal of Sociology.

[46]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[47]  Mingjie Sun,et al.  Data Poisoning Attack against Unsupervised Node Embedding Methods , 2018, ArXiv.

[48]  M. Newman,et al.  Vertex similarity in networks. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[49]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[50]  Stephan Günnemann,et al.  Adversarial Attacks on Node Embeddings , 2018, ICML 2019.

[51]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.