Streaming Active Learning with Deep Neural Networks

Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan T. Ash
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30005-30021, 2023.

Abstract

Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the entire dataset ahead of time. This paper proposes VeSSAL, a new algorithm for batch active learning with deep neural networks in streaming settings, which samples groups of points to query for labels at the moment they are encountered. Our approach trades off between uncertainty and diversity of queried samples to match a desired query rate without requiring any hand-tuned hyperparameters. Altogether, we expand the applicability of deep neural networks to realistic active learning scenarios, such as applications relevant to HCI and large, fractured datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-saran23a, title = {Streaming Active Learning with Deep Neural Networks}, author = {Saran, Akanksha and Yousefi, Safoora and Krishnamurthy, Akshay and Langford, John and Ash, Jordan T.}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {30005--30021}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/saran23a/saran23a.pdf}, url = {https://proceedings.mlr.press/v202/saran23a.html}, abstract = {Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the entire dataset ahead of time. This paper proposes VeSSAL, a new algorithm for batch active learning with deep neural networks in streaming settings, which samples groups of points to query for labels at the moment they are encountered. Our approach trades off between uncertainty and diversity of queried samples to match a desired query rate without requiring any hand-tuned hyperparameters. Altogether, we expand the applicability of deep neural networks to realistic active learning scenarios, such as applications relevant to HCI and large, fractured datasets.} }
Endnote
%0 Conference Paper %T Streaming Active Learning with Deep Neural Networks %A Akanksha Saran %A Safoora Yousefi %A Akshay Krishnamurthy %A John Langford %A Jordan T. Ash %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-saran23a %I PMLR %P 30005--30021 %U https://proceedings.mlr.press/v202/saran23a.html %V 202 %X Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the entire dataset ahead of time. This paper proposes VeSSAL, a new algorithm for batch active learning with deep neural networks in streaming settings, which samples groups of points to query for labels at the moment they are encountered. Our approach trades off between uncertainty and diversity of queried samples to match a desired query rate without requiring any hand-tuned hyperparameters. Altogether, we expand the applicability of deep neural networks to realistic active learning scenarios, such as applications relevant to HCI and large, fractured datasets.
APA
Saran, A., Yousefi, S., Krishnamurthy, A., Langford, J. & Ash, J.T.. (2023). Streaming Active Learning with Deep Neural Networks. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:30005-30021 Available from https://proceedings.mlr.press/v202/saran23a.html.

Related Material