Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.10629 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910527800737792 |
|---|---|
| author | Eshuijs, Leon Wang, Shihan Fokkens, Antske |
| author_facet | Eshuijs, Leon Wang, Shihan Fokkens, Antske |
| contents | Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its capacity for learning through interaction and adjusting reward functions to encourage desired behaviors, emerges as a promising tool in this domain. In this paper, we explore the usage of RL to address bias in imbalanced classification by scaling the reward function to mitigate bias. We employ the contextual multi-armed bandit framework and adapt three popular RL algorithms to suit our objectives, demonstrating a novel approach to mitigating bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10629 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Balancing the Scales: Reinforcement Learning for Fair Classification Eshuijs, Leon Wang, Shihan Fokkens, Antske Machine Learning Computation and Language Computers and Society Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its capacity for learning through interaction and adjusting reward functions to encourage desired behaviors, emerges as a promising tool in this domain. In this paper, we explore the usage of RL to address bias in imbalanced classification by scaling the reward function to mitigate bias. We employ the contextual multi-armed bandit framework and adapt three popular RL algorithms to suit our objectives, demonstrating a novel approach to mitigating bias. |
| title | Balancing the Scales: Reinforcement Learning for Fair Classification |
| topic | Machine Learning Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2407.10629 |