VTruST: Controllable value function based subset selection for Data-Centric Trustworthy AI
This addresses the need for trustworthy AI in high-stakes applications by enabling user control over trade-offs between metrics, though it appears incremental as it builds on existing subset selection methods.
The authors tackled the problem of balancing multiple trustworthiness metrics (e.g., fairness, robustness, accuracy) in AI by proposing VTruST, a controllable framework for data-centric trustworthy AI that uses an online value-function-based subset selection algorithm, and experimental results show it outperforms state-of-the-art baselines on social, image, and scientific datasets.
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.