VTruST: Controllable value function based subset selection for Data-Centric Trustworthy AI
Keywords: Data-centric trustworthy AI, online OMP, value function, user controlled tradeoff, data-centric explanation, fairness, robustness, accuracy
TL;DR: A general data-centric framework to achieve user-controlled tradeoffs between different trustworthiness metrics.
Abstract: Trustworthy AI is crucial to the widespread adoption of AI in high-stakes applications with \textit{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.
Primary Subject Area: Data-centric explainable AI
Paper Type: Research paper: up to 8 pages
Participation Mode: In-person
Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.
Submission Number: 90
Loading