Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible
This work addresses the need for interpretable and reliable decision support in clinical applications like HIV treatment and MDD management, though it appears incremental as it builds on existing mixture-of-experts frameworks.
The authors tackled the problem of integrating human expertise with machine learning in decision-making by proposing Preferential MoE, a model that uses a data-based classifier only when necessary to maintain predictive performance, resulting in an interpretable gating function that minimizes classification errors.
We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance. Our model exhibits an interpretable gating function that provides information on when human rules should be followed or avoided. The gating function is maximized for using human-based rules, and classification errors are minimized. We propose solving a coupled multi-objective problem with convex subproblems. We develop approximate algorithms and study their performance and convergence. Finally, we demonstrate the utility of Preferential MoE on two clinical applications for the treatment of Human Immunodeficiency Virus (HIV) and management of Major Depressive Disorder (MDD).