Scalable greedy algorithms for transfer learning

Ilja Kuzborskij, Francesco Orabona, Barbara Caputo

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

In this paper we consider the binary transfer learning problem, focusing on how to select and combine sources from a large pool to yield a good performance on a target task. Constraining our scenario to real world, we do not assume the direct access to the source data, but rather we employ the source hypotheses trained from them. We propose an efficient algorithm that selects relevant source hypotheses and feature dimensions simultaneously, building on the literature on the best subset selection problem. Our algorithm achieves state-of-the-art results on three computer vision datasets, substantially outperforming both transfer learning and popular feature selection baselines in a small-sample setting. We also present a randomized variant that achieves the same results with the computational cost independent from the number of source hypotheses and feature dimensions. Also, we theoretically prove that, under reasonable assumptions on the source hypotheses, our algorithm can learn effectively from few examples.
Original languageEnglish (US)
Pages (from-to)174-185
Number of pages12
JournalComputer Vision and Image Understanding
Volume156
DOIs
StatePublished - Mar 1 2017
Externally publishedYes

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Scalable greedy algorithms for transfer learning'. Together they form a unique fingerprint.

Cite this