A Meta-heuristic Approach to Estimate and Explain Classifier Uncertainty
This work addresses the need for model-agnostic and understandable uncertainty estimation to improve trust in ML models, especially for laypersons in critical domains, though it appears incremental in its approach.
The paper tackled the problem of making ML models more trustworthy by enabling them to express uncertainty in decision-making, particularly for end-users in domains like medicine, and it resulted in a meta-heuristic framework that outperformed predicted probabilities in identifying instances at risk of misclassification.
Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making allowing users to know when to ignore the model's recommendations. However, existing approaches for quantifying decision-making uncertainty are not model-agnostic, or they rely on complex statistical derivations that are not easily understood by laypersons or end-users, making them less useful for explaining the model's decision-making process. This work proposes a set of class-independent meta-heuristics that can characterize the complexity of an instance in terms of factors are mutually relevant to both human and ML decision-making. The measures are integrated into a meta-learning framework that estimates the risk of misclassification. The proposed framework outperformed predicted probabilities in identifying instances at risk of being misclassified. The proposed measures and framework hold promise for improving model development for more complex instances, as well as providing a new means of model abstention and explanation.