Work‎ > ‎Projects‎ > ‎

A Commercial Software of Data Mining in Large-scale Graphs and Social Networks

posted Oct 23, 2011, 9:13 PM by Botao Hu   [ updated Nov 1, 2011, 3:59 PM ]
Development Conductor and Core Developer
Jun 2011 - Oct 2011
Supervised by Qiang Yang
Hong Kong University of Science and Technology, Hong Kong

This project is aimed to build a library for graph mining, which can efficiently handle large scale graphs (5M nodes, 10M edges at least), and implements not only the basic statistics and operations of graph, but also the-state-of-the-art methods/algorithms in the five topics/problems of graph mining: Link-based Objective Ranking, Link-based Object Classification, Predicting Link Existence, Link Cardinality Estimation, and Group Detection/Community Detection. 

My plenty of time, approximately 4 months, was devoted to this project. 50k+ lines of code was involved, among which at least 30k+ lines was written by myself independently.