Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.08921 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909203289866240 |
|---|---|
| author | Heuillet, Maxime Ahmad, Ola Durand, Audrey |
| author_facet | Heuillet, Maxime Ahmad, Ola Durand, Audrey |
| contents | We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We propose a novel foundation for OAL tasks based on partial monitoring, a theoretical framework specialized in online learning from partially informative actions. We show that previously studied binary and multi-class OAL tasks are instances of partial monitoring. We expand the real-world potential of OAL by introducing a new class of cost-sensitive OAL tasks. We propose NeuralCBP, the first PM strategy that accounts for predictive uncertainty with deep neural networks. Our extensive empirical evaluation on open source datasets shows that NeuralCBP has favorable performance against state-of-the-art baselines on multiple binary, multi-class and cost-sensitive OAL tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08921 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Active Learning Meets the Partial Monitoring Framework Heuillet, Maxime Ahmad, Ola Durand, Audrey Machine Learning We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We propose a novel foundation for OAL tasks based on partial monitoring, a theoretical framework specialized in online learning from partially informative actions. We show that previously studied binary and multi-class OAL tasks are instances of partial monitoring. We expand the real-world potential of OAL by introducing a new class of cost-sensitive OAL tasks. We propose NeuralCBP, the first PM strategy that accounts for predictive uncertainty with deep neural networks. Our extensive empirical evaluation on open source datasets shows that NeuralCBP has favorable performance against state-of-the-art baselines on multiple binary, multi-class and cost-sensitive OAL tasks. |
| title | Neural Active Learning Meets the Partial Monitoring Framework |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.08921 |