Scaling factorization machines to relational data


Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

RENDLE, Steffen, 2013. Scaling factorization machines to relational data. In: Proceedings of the VLDB Endowment. 6(5), pp. 337-348. ISSN 2150-8097

@article{Rendle2013Scali-26517, title={Scaling factorization machines to relational data}, year={2013}, number={5}, volume={6}, issn={2150-8097}, journal={Proceedings of the VLDB Endowment}, pages={337--348}, author={Rendle, Steffen} }

terms-of-use Scaling factorization machines to relational data Rendle, Steffen 2014-02-21T12:08:42Z eng Proceedings of the VLDB Endowment ; 6 (2013), 5. - S. 337-348 The most common approach in predictive modeling is to describe cases with feature vectors (aka design matrix). Many machine learning methods such as linear regression or support vector machines rely on this representation. However, when the underlying data has strong relational patterns, especially relations with high cardinality, the design matrix can get very large which can make learning and prediction slow or even infeasible.<br />This work solves this issue by making use of repeating patterns in the design matrix which stem from the underlying relational structure of the data. It is shown how coordinate descent learning and Bayesian Markov Chain Monte Carlo inference can be scaled for linear regression and factorization machine models. Empirically, it is shown on two large scale and very competitive datasets (Netflix prize, KDDCup 2012), that (1) standard learning algorithms based on the design matrix representation cannot scale to relational predictor variables, (2) the proposed new algorithms scale and (3) the predictive quality of the proposed generic feature-based approach is as good as the best specialized models that have been tailored to the respective tasks. 2014-02-21T12:08:42Z 2013 Rendle, Steffen

Das Dokument erscheint in:

KOPS Suche


Mein Benutzerkonto