High stakes decision making requires that any decision support systems must be able to come up with plausible explanations about the decisions they propose to the user. Several popular approaches to explaining black-box AI systems, such as neural networks, focus either on highlighting the features that matter the most in one particular decision as in the SHAP models, or on developing a local to the particular instance data model that is explainable by nature, such as a decision tree. ML systems that are by default explainable and/or interpretable, such as decision trees, or rule-based systems do not require such third-party approaches, as they are themselves explainable. Nevertheless, presenting a consistent (small) set of features to the users as explanations for any given proposed decision can increase the confidence of the users towards the reliability of the system. For this reason, we have developed a system that given a set of rules that hold on a training dataset, finds a minimal cardinality set of features that are used in a set of rules that together cover the entire training dataset. We develop a parallel heuristic algorithm for finding such a minimal variables set, and we show it outperforms all state-of-the-art optimization solvers for finding the solution to a MIP formulation of the problem. Experiments with data from use cases applying AI in public policy decision making as well as in medical use cases show that the proposed small set of features is sufficient to explain all the cases in the test dataset via rules containing only variables from the proposed set of features.
Disclaimer: this talk is based on the paper: “Feature Selection via Minimal Covering Sets for Industrial Internet of Things Applications”, by I.T. Christou, J. Soldatos, T. Papadakis, D. Gutierrez-Rojas, P. Nardelli, IEEE DCOSS-IoT, Pafos, Cyprus, 2023.
Prof. Ioannis T. Christou is a chartered electrical engineer and holds a Dipl. Ing. in Electrical Engineering from the National Technical University of Athens, an M.Sc. and Ph.D. in Computer Sciences from the University of Wisconsin at Madison, WI, USA, and an MBA from the AthensMBA joint program between NTUA and the Athens University of Economics and Business (AUEB). He has worked for many organizations in the USA and in Greece, including AT&T Bell Labs, Delta Technology Inc., Lucent Technologies Bell Labs Hellas, Intracom S.A. and others. He has also taught as Adjunct Professor at the Carnegie-Mellon University, Pittsburgh, PA, Aalborg University, Aalborg, Denmark, the Dept. of Computer Engineering and Informatics, University of Patras, Greece, Athens Information Technology and others. Currently, he is an Associate Professor at the Dept. of Information Technology at the American College of Greece, and he is a Sr. Research Data Scientist at NetCompany-Intrasoft S.A., Luxemburg. His research interests are in AI, deep learning, parallel computing, optimization and data mining. He has more than 100 publications in peer-reviewed journals and conferences such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Intelligent Systems, IEEE Software etc.