Front Page NewsTSSG News

TSSG release Open Source Code

By 5th October 2012 No Comments

5th October 2012


Telecommunications Software & Systems Group (TSSG) Research Master and developer  Biao Xu, recently released code as open source in TSSG’s page at Github. The source code of MRGanter+ algorithm, which was included in a recent paper “Distributed Formal Concept Analysis Algorithms Based on an Iterative MapReduce Framework” was presented at ICFCA 2012, in Leuven, Belgium, 6-10th May 2012.

MRGanter+is a distributed Formal Concept Analysis algorithm based on Gater’s algorithm (known as NextClosure) and an iterative MapReduce framework, Twister. NextClosure calculates closures in lectic ordering to ensure every concept appears only once. This approach allows a single concept to be tested with the closure validation condition during each iteration. This is efficient when the algorithm runs on a single machine. For multi-machine computation, the extra computation and redundancy resulting from keeping only one concept after each iteration across many machines is costly. By modifying NextClosure to reduce the number of iterations and name the corresponding distributed algorithm MRGanter+ rather than using redundancy checking, many closures as possible can be kept in each iteration; All closures are maintained and used to generate the next batch of closures. The code is hosted online and can be viewed here.

Biao Xu is part of the Data Mining and Social Computing Research Unit at TSSG, managed by Eric Robson and focuses on accurately discovering the maximum amount of knowledge in the most efficient manner from increasingly large databases. To achieve this we research the full data analysis life cycle – from data gathering to data cleaning and warehousing through to modelling and presentation of results.


For More Information, please see links below:

Learn more about Biao Xu, click here

Learn more about the Data Mining and Social Computing Research Unit at TSS, click here

Learn more about Eric Robson, click here

To view the paper, click here

To view the source code of MRGanter+ algorithm, click here