Large scale inference in the Infinite Relational Model: Gibbs sampling is not enough

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedings – Annual report year: 2013Researchpeer-review

View graph of relations

The stochastic block-model and its non-parametric extension, the Infinite Relational Model (IRM), have become key tools for discovering group-structure in complex networks. Identifying these groups is a combinatorial inference problem which is usually solved by Gibbs sampling. However, whether Gibbs sampling suffices and can be scaled to the modeling of large scale real world complex networks has not been examined sufficiently. In this paper we evaluate the performance and mixing ability of Gibbs sampling in the Infinite Relational Model (IRM) by implementing a high performance Gibbs sampler. We find that Gibbs sampling can be computationally scaled to handle millions of nodes and billions of links. Investigating the behavior of the Gibbs sampler for different sizes of networks we find that the mixing ability decreases drastically with the network size, clearly indicating a need for better sampling strategies.
Original languageEnglish
Title of host publication2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
Number of pages6
Publication date2013
Publication statusPublished - 2013
Event2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) - Southampton, United Kingdom
Duration: 22 Sep 201325 Sep 2013


Workshop2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
CountryUnited Kingdom
Internet address
SeriesMachine Learning for Signal Processing
CitationsWeb of Science® Times Cited: No match on DOI

    Research areas

  • Bioengineering, Communication, Networking and Broadcast Technologies, Computing and Processing, General Topics for Engineers, Robotics and Control Systems, Signal Processing and Analysis, Transportation

ID: 61213094