• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Greedy Regularized Least-Squares for Multi-Task Learning

Pekka Naula, Tapio Pahikkala, Antti Airola, Tapio Salakoski, Greedy Regularized Least-Squares for Multi-Task Learning. In: Myra Spiliopoulou, Haixun Wang, Diane Cook, Jian Pei, Wei Wang, Osmar Zaïane, Xindong Wu (Eds.), 11th IEEE International Conference on Data Mining Workshops (ICDMW'11), 527-533, IEEE Computer Society, 2011.

http://dx.doi.org/10.1109/ICDMW.2011.91

Abstract:

Multi-task feature selection refers to the problem of selecting a common predictive set of features over multiple related learning tasks. The problem is encountered for example in applications, where one can afford only a limited set of feature extractors for solving several tasks. In this work, we present a regularized least-squares (RLS) based algorithm for multi-task greedy forward feature selection. The method selects features jointly for all the tasks by using leave-one-out cross-validation error averaged over the tasks as the selection criterion. While a straightforward implementation of the approach by combining a wrapper algorithm with a black-box RLS training method would have impractical computational costs, we achieve linear time complexity for the training algorithm through the use of matrix algebra based computational shortcuts. In our experiments on insurance and speech classification data sets the proposed method shows a better prediction performance than baseline methods that select the same number of features independently.

Files:

Full publication in PDF-format

BibTeX entry:

@INPROCEEDINGS{inpNaPaAiSa11a,
  title = {Greedy Regularized Least-Squares for Multi-Task Learning},
  booktitle = {11th IEEE International Conference on Data Mining Workshops (ICDMW'11)},
  author = {Naula, Pekka and Pahikkala, Tapio and Airola, Antti and Salakoski, Tapio},
  editor = {Spiliopoulou, Myra and Wang, Haixun and Cook, Diane and Pei, Jian and Wang, Wei and Zaïane, Osmar and Wu, Xindong},
  publisher = {IEEE Computer Society},
  pages = {527-533},
  year = {2011},
  keywords = {Feature Subset Selection, Multi-Task Learning, Budgeted Learning, Regularized Least-Squares},
}

Belongs to TUCS Research Unit(s): Algorithmics and Computational Intelligence Group (ACI), Turku BioNLP Group

Edit publication