no code implementations • 19 Nov 2023 • Ngoc Bui, Duy Nguyen, Man-Chung Yue, Viet Anh Nguyen
Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency and hence ethics of machine learning models.
1 code implementation • 22 Feb 2023 • Duy Nguyen, Ngoc Bui, Viet Anh Nguyen
The experimental results show that our method produces a set of recourses that are close to the data manifold while delivering a better cost-diversity trade-off than existing approaches.
1 code implementation • 22 Feb 2023 • Duy Nguyen, Ngoc Bui, Viet Anh Nguyen
To redress this shortcoming, we propose the Distributionally Robust Recourse Action (DiRRAc) framework, which generates a recourse action that has a high probability of being valid under a mixture of model shifts.
no code implementations • 16 Aug 2022 • Ngoc Bui, Phi Le Nguyen, Viet Anh Nguyen, Phan Thuan Do
We then use a deep neural network to parametrize this charging policy, which will be trained by reinforcement learning techniques.
no code implementations • 22 Jun 2022 • Tuan-Duy H. Nguyen, Ngoc Bui, Duy Nguyen, Man-Chung Yue, Viet Anh Nguyen
Algorithmic recourse aims to recommend an informative feedback to overturn an unfavorable machine learning decision.
1 code implementation • ICLR 2022 • Ngoc Bui, Duy Nguyen, Viet Anh Nguyen
Counterfactual explanations are attracting significant attention due to the flourishing applications of machine learning models in consequential domains.