Tampere University of Technology

TUTCRIS Research Portal

Sparse nonparametric topic model for transfer learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Publisheri6doc.com publication
Pages269-274
Number of pages6
ISBN (Print)9782874190490
Publication statusPublished - 2012
Publication typeA4 Article in a conference publication
Event20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 - Bruges, Belgium
Duration: 25 Apr 201227 Apr 2012

Conference

Conference20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012
CountryBelgium
CityBruges
Period25/04/1227/04/12

Abstract

Count data arises for example in bioinformatics or analysis of text documents represented as word count vectors. With several data sets available from related sources, exploiting their similarities by transfer learning can improve models compared to modeling sources independently. We introduce a Bayesian generative transfer learning model which represents similarity across document collections by sparse sharing of latent topics controlled by an Indian Buffet Process. Unlike Hierarchical Dirichlet Process based multi-task learning, our model decouples topic sharing probability from topic strength, making sharing of low-strength topics easier, and outperforms the HDP approach in experiments.