GraphFederator: Federated Visual Analysis for Multi-party Graphs

This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization process. The new federation framework consists of a shared module that is responsible for joint modeling and analysis, and a set of local modules that run on respective graph data. Specifically, we propose a federated graph representation model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules. We also design multiple visualization views for joint visualization, exploration, and analysis of multi-party graphs. Experimental results with two datasets demonstrate the effectiveness of our approach.

[1]  Peng Cui,et al.  MVAN: Multi-view Attention Networks for Real Money Trading Detection in Online Games , 2019, KDD.

[2]  Hanghang Tong,et al.  g-Miner: Interactive Visual Group Mining on Multivariate Graphs , 2015, CHI.

[3]  Stephen G. Kobourov,et al.  Group-Level Graph Visualization Taxonomy , 2014, EuroVis.

[4]  Ross Maciejewski,et al.  A Visual Analytics Framework for Spatiotemporal Trade Network Analysis , 2019, IEEE Transactions on Visualization and Computer Graphics.

[5]  Peter Richtárik,et al.  Federated Optimization: Distributed Machine Learning for On-Device Intelligence , 2016, ArXiv.

[6]  Arjan Kuijper,et al.  Visual Analysis of Large Graphs: State‐of‐the‐Art and Future Research Challenges , 2011, Eurographics.

[7]  Ching-Yung Lin,et al.  TargetVue: Visual Analysis of Anomalous User Behaviors in Online Communication Systems , 2016, IEEE Transactions on Visualization and Computer Graphics.

[8]  L. Sweeney Simple Demographics Often Identify People Uniquely , 2000 .

[9]  Sungpack Hong,et al.  PGX.D: a fast distributed graph processing engine , 2015, SC15: International Conference for High Performance Computing, Networking, Storage and Analysis.

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

[11]  Ronald L. Rivest,et al.  ON DATA BANKS AND PRIVACY HOMOMORPHISMS , 1978 .

[12]  Vitaly Shmatikov,et al.  How To Backdoor Federated Learning , 2018, AISTATS.

[13]  Shijun Liu,et al.  SGNN: A Graph Neural Network Based Federated Learning Approach by Hiding Structure , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[14]  Ninghui Li,et al.  t-Closeness: Privacy Beyond k-Anonymity and l-Diversity , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[15]  Tianjian Chen,et al.  Federated Machine Learning: Concept and Applications , 2019 .

[16]  Kannan Ramchandran,et al.  Speeding Up Distributed Machine Learning Using Codes , 2015, IEEE Transactions on Information Theory.

[17]  John T. Stasko,et al.  Tasks for Multivariate Network Analysis , 2013, Multivariate Network Visualization.

[18]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

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

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

[21]  Wei Chen,et al.  A survey of network anomaly visualization , 2017, Science China Information Sciences.

[22]  Peter Richtárik,et al.  Federated Learning: Strategies for Improving Communication Efficiency , 2016, ArXiv.

[23]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[24]  Aaron Q. Li,et al.  Parameter Server for Distributed Machine Learning , 2013 .

[25]  M. Narasimha Murty,et al.  Genetic K-means algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[26]  Kunal Talwar,et al.  Mechanism Design via Differential Privacy , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[27]  Kwan-Liu Ma,et al.  A Utility-Aware Visual Approach for Anonymizing Multi-Attribute Tabular Data , 2018, IEEE Transactions on Visualization and Computer Graphics.

[28]  Zhou Zhao,et al.  NGUARD: A Game Bot Detection Framework for NetEase MMORPGs , 2018, KDD.

[29]  Tara Javidi,et al.  Peer-to-peer Federated Learning on Graphs , 2019, ArXiv.

[30]  Alexander Lex,et al.  The State of the Art in Visualizing Multivariate Networks , 2019, Comput. Graph. Forum.

[31]  Minsuk Kahng,et al.  Scalable graph exploration and visualization: Sensemaking challenges and opportunities , 2015, 2015 International Conference on Big Data and Smart Computing (BIGCOMP).

[32]  Tim Verbelen,et al.  A Survey on Distributed Machine Learning , 2019, ACM Comput. Surv..

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

[34]  Sarvar Patel,et al.  Practical Secure Aggregation for Privacy-Preserving Machine Learning , 2017, IACR Cryptol. ePrint Arch..

[35]  Amit Sahai,et al.  Secure Multi-Party Computation , 2013 .

[36]  Marina Blanton,et al.  Secure Multiparty Computation , 2011, Encyclopedia of Cryptography and Security.

[37]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[38]  Mauro Barni,et al.  Oblivious Neural Network Computing via Homomorphic Encryption , 2007, EURASIP J. Inf. Secur..

[39]  Latanya Sweeney,et al.  k-Anonymity: A Model for Protecting Privacy , 2002, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[40]  Tim Weninger,et al.  Thinking Like a Vertex , 2015, ACM Comput. Surv..

[41]  ASHWIN MACHANAVAJJHALA,et al.  L-diversity: privacy beyond k-anonymity , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[42]  Ryan A. Rossi,et al.  The Network Data Repository with Interactive Graph Analytics and Visualization , 2015, AAAI.

[43]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[44]  Linyuan Lu,et al.  Link Prediction in Complex Networks: A Survey , 2010, ArXiv.

[45]  K. Mani Chandy,et al.  Distributed computation on graphs: shortest path algorithms , 1982, CACM.

[46]  Michael C. Hout,et al.  Multidimensional Scaling , 2003, Encyclopedic Dictionary of Archaeology.

[47]  Tamara Munzner,et al.  A Multi-Level Typology of Abstract Visualization Tasks , 2013, IEEE Transactions on Visualization and Computer Graphics.

[48]  Thomas S. Huang,et al.  One-class SVM for learning in image retrieval , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[49]  Jean-Daniel Fekete,et al.  Task taxonomy for graph visualization , 2006, BELIV '06.

[50]  Wei Li,et al.  Tux2: Distributed Graph Computation for Machine Learning , 2017, NSDI.

[51]  Daniel A. Keim,et al.  A Survey on Visual Analytics of Social Media Data , 2016, IEEE Transactions on Multimedia.

[52]  Blaise Agüera y Arcas,et al.  Federated Learning of Deep Networks using Model Averaging , 2016, ArXiv.

[53]  Kwan-Liu Ma,et al.  GraphProtector: A Visual Interface for Employing and Assessing Multiple Privacy Preserving Graph Algorithms , 2019, IEEE Transactions on Visualization and Computer Graphics.

[54]  Kumar Sricharan,et al.  Graph Analysis for Detecting Fraud, Waste, and Abuse in Healthcare Data , 2015, AI Mag..

[55]  Jian Zhao,et al.  Egocentric Analysis of Dynamic Networks with EgoLines , 2016, CHI.

[56]  Lalana Kagal,et al.  PrivacyFL: A Simulator for Privacy-Preserving and Secure Federated Learning , 2020, CIKM.