VTruST: Controllable value function based subset selection for Data-Centric Trustworthy AI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917608308080640 |
|---|---|
| author | Das, Soumi Nag, Shubhadip Sharma, Shreyyash Bhattacharya, Suparna Bhattacharya, Sourangshu |
| author_facet | Das, Soumi Nag, Shubhadip Sharma, Shreyyash Bhattacharya, Suparna Bhattacharya, Sourangshu |
| contents | Trustworthy AI is crucial to the widespread adoption of AI in high-stakes applications with fairness, robustness, and accuracy being some of the key trustworthiness metrics. In this work, we propose a controllable framework for data-centric trustworthy AI (DCTAI)- VTruST, that allows users to control the trade-offs between the different trustworthiness metrics of the constructed training datasets. A key challenge in implementing an efficient DCTAI framework is to design an online value-function-based training data subset selection algorithm. We pose the training data valuation and subset selection problem as an online sparse approximation formulation. We propose a novel online version of the Orthogonal Matching Pursuit (OMP) algorithm for solving this problem. Experimental results show that VTruST outperforms the state-of-the-art baselines on social, image, and scientific datasets. We also show that the data values generated by VTruST can provide effective data-centric explanations for different trustworthiness metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VTruST: Controllable value function based subset selection for Data-Centric Trustworthy AI Das, Soumi Nag, Shubhadip Sharma, Shreyyash Bhattacharya, Suparna Bhattacharya, Sourangshu Machine Learning Trustworthy AI is crucial to the widespread adoption of AI in high-stakes applications with fairness, robustness, and accuracy being some of the key trustworthiness metrics. In this work, we propose a controllable framework for data-centric trustworthy AI (DCTAI)- VTruST, that allows users to control the trade-offs between the different trustworthiness metrics of the constructed training datasets. A key challenge in implementing an efficient DCTAI framework is to design an online value-function-based training data subset selection algorithm. We pose the training data valuation and subset selection problem as an online sparse approximation formulation. We propose a novel online version of the Orthogonal Matching Pursuit (OMP) algorithm for solving this problem. Experimental results show that VTruST outperforms the state-of-the-art baselines on social, image, and scientific datasets. We also show that the data values generated by VTruST can provide effective data-centric explanations for different trustworthiness metrics. |
| title | VTruST: Controllable value function based subset selection for Data-Centric Trustworthy AI |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.05174 |