International Journal of Parallel Programming

, Volume 44, Issue 3, pp 663–685

Relational Learning with GPUs: Accelerating Rule Coverage

  • Carlos Alberto Martínez-Angeles
  • Haicheng Wu
  • Inês Dutra
  • Vítor Santos Costa
  • Jorge Buenabad-Chávez
Article

DOI: 10.1007/s10766-015-0364-7

Cite this article as:
Martínez-Angeles, C.A., Wu, H., Dutra, I. et al. Int J Parallel Prog (2016) 44: 663. doi:10.1007/s10766-015-0364-7

Abstract

Relational learning algorithms mine complex databases for interesting patterns. Usually, the search space of patterns grows very quickly with the increase in data size, making it impractical to solve important problems. In this work we present the design of a relational learning system, that takes advantage of graphics processing units (GPUs) to perform the most time consuming function of the learner, rule coverage. To evaluate performance, we use four applications: a widely used relational learning benchmark for predicting carcinogenesis in rodents, an application in chemo-informatics, an application in opinion mining, and an application in mining health record data. We compare results using a single and multiple CPUs in a multicore host and using the GPU version. Results show that the GPU version of the learner is up to eight times faster than the best CPU version.

Keywords

Relational learning Inductive logic Logic programming Datalog Relational databases Parallel computing GPUs 

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Carlos Alberto Martínez-Angeles
    • 1
  • Haicheng Wu
    • 3
  • Inês Dutra
    • 2
  • Vítor Santos Costa
    • 2
  • Jorge Buenabad-Chávez
    • 1
  1. 1.Departamento de ComputaciónCINVESTAV-IPNMexicoMexico
  2. 2.Departmento de Ciência de ComputadoresCRACS INESC-TEC LA and Universidade do PortoPortoPortugal
  3. 3.Georgia Institute of TechnologyAtlantaUSA