Deep Active Learning with a Neural Architecture Search
Yonatan Geifman, Ran El-Yaniv
We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby the learning algorithm searches for effective architectures on the fly, while actively learning. We apply our strategy using three known querying techniques (softmax response, MC-dropout, and coresets) and show that the proposed approach overwhelmingly outperforms active learning using fixed architectures.
@inproceedings{NEURIPS2019_b59307fd, author = {Geifman, Yonatan and El-Yaniv, Ran}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch'{e}-Buc and E. Fox and R. Garnett}, pages = {5976--5986}, publisher = {Curran Associates, Inc.}, title = {Deep Active Learning with a Neural Architecture Search}, url = {https://proceedings.neurips.cc/paper/2019/file/b59307fdacf7b2db12ec4bd5ca1caba8-Paper.pdf}, volume = {32}, year = {2019} }