Or Litany, Daniel Freedman, ICLR workshop on Learning from Limited Labeled Data, 2019. *Best Paper Award*

Abstract:

We present SOSELETO (SOurce SELEction for Target Optimization), a new method for exploiting a source dataset to solve a classification problem on a target dataset. SOSELETO is based on the following simple intuition: some source examples are more informative than others for the target problem. To capture this intuition, source samples are each given weights; these weights are solved for jointly with the source and target classification problems via a bilevel optimization scheme. The target therefore gets to choose the source samples which are most informative for its own classification task. Furthermore, the bilevel nature of the optimization acts as a kind of regularization on the target, mitigating overfitting. SOSELETO may be applied to both classic transfer learning, as well as the problem of training on datasets with noisy labels; we show state of the art results on both of these problems.

Bibtex:

@article{lf-soseleto-19,
  Author    = {Or Litany and Daniel Freedman},
  Title     = {SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels},
  Journal   = {arXiv preprint arXiv:1805.09622},
  Year      = {2018}}