Big Graph Mining For The Web And Social Media: Algorithms, Anomaly Detection, And Applications

ABSTRACTGraphs are everywhere: social networks, computer net- works, mobile call networks, the World Wide Web, protein interaction networks, and many more. The lower cost of disk storage, the success of social networking websites and Web 2.0 applications, and the high availability of data sources lead to graphs being generated at unprecedented size. They are now measured in terabytes or even petabytes, with more than billions of nodes and edges. Finding patterns on large graphs have a lot of applica- tions including cyber security on the Web, social media min- ing (Facebook, Twitter), and fraud detection, among others. This tutorial will cover topics related to finding patterns and anomalies and sensemaking in large-scale graphs with appli- cations to real-world problems in social media and the Web. Specifically, we aim to answer the following questions: How can we scale up graph mining algorithms for massive graphs with billions of edges? How can we find anomalies in such large-scale graphs? How can we make sense of disk-resident large graphs, what and how can we do visual analytics? How can we use the algorithms and anomaly detection techniques to solve challenging real-world problems that play key role in social media and the Web? Our tutorial consists of three main parts. We start with scalable graph mining algorithms for billion-scale graphs, in- cluding structure analysis, eigensolvers, storage and index- ing, and graph layout and graph compression. Next we de- scribe anomaly detection techniques for large scale graphs with applications on social media. Finally, we discuss vi- sual analytics techniques which leverage these algorithms and anomaly detection techniques in the previous parts.