Learning Active Learning from Data

Ksenia Konyushkova; Raphael Sznitman; Pascal Fua

NeurIPS 2017poster411 citations

Learning Active Learning from Data

Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

Abstract

In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection procedure as a regression problem we are not restricted to working with existing AL heuristics; instead, we learn strategies based on experience from previous AL outcomes. We show that a strategy can be learnt either from simple synthetic 2D datasets or from a subset of domain-specific data. Our method yields strategies that work well on real data from a wide range of domains.

BibTeX

@inproceedings{NIPS2017_8ca8da41,
 author = {Konyushkova, Ksenia and Sznitman, Raphael and Fua, Pascal},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Learning Active Learning from Data},
 url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/8ca8da41fe1ebc8d3ca31dc14f5fc56c-Paper.pdf},
 volume = {30},
 year = {2017}
}