English

Deep Multi-Instance Transfer Learning

Machine Learning 2014-12-11 v2 Machine Learning

Abstract

We present a new approach for transferring knowledge from groups to individuals that comprise them. We evaluate our method in text, by inferring the ratings of individual sentences using full-review ratings. This approach, which combines ideas from transfer learning, deep learning and multi-instance learning, reduces the need for laborious human labelling of fine-grained data when abundant labels are available at the group level.

Keywords

Cite

@article{arxiv.1411.3128,
  title  = {Deep Multi-Instance Transfer Learning},
  author = {Dimitrios Kotzias and Misha Denil and Phil Blunsom and Nando de Freitas},
  journal= {arXiv preprint arXiv:1411.3128},
  year   = {2014}
}
R2 v1 2026-06-22T06:56:00.456Z