Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection
This addresses the problem of inefficient preference selection for decision-makers in multi-objective optimization, though it is incremental as it builds on existing explainable AI methods by adding output-focused explanations.
The paper tackles the challenge of preference elicitation in Preference Bayesian optimization by introducing MOLONE, a comparative explanation method that highlights input and output importance to help decision-makers understand trade-offs between objectives, resulting in improved convergence in benchmark tests and a user study showing accelerated convergence in human-in-the-loop scenarios.
This paper introduces Multi-Output LOcal Narrative Explanation (MOLONE), a novel comparative explanation method designed to enhance preference selection in human-in-the-loop Preference Bayesian optimization (PBO). The preference elicitation in PBO is a non-trivial task because it involves navigating implicit trade-offs between vector-valued outcomes, subjective priorities of decision-makers, and decision-makers' uncertainty in preference selection. Existing explainable AI (XAI) methods for BO primarily focus on input feature importance, neglecting the crucial role of outputs (objectives) in human preference elicitation. MOLONE addresses this gap by providing explanations that highlight both input and output importance, enabling decision-makers to understand the trade-offs between competing objectives and make more informed preference selections. MOLONE focuses on local explanations, comparing the importance of input features and outcomes across candidate samples within a local neighborhood of the search space, thus capturing nuanced differences relevant to preference-based decision-making. We evaluate MOLONE within a PBO framework using benchmark multi-objective optimization functions, demonstrating its effectiveness in improving convergence compared to noisy preference selections. Furthermore, a user study confirms that MOLONE significantly accelerates convergence in human-in-the-loop scenarios by facilitating more efficient identification of preferred options.