Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates
This work addresses the need for more interpretable and efficient uncertainty explanations in machine learning, though it appears incremental by building on existing counterfactual explanation methods.
The paper tackles the problem of interpreting uncertainty estimates from probabilistic models by broadening single counterfactual explanations to sets of diverse explanations and proposing an amortized method for efficient transformation of uncertain inputs, showing that these approaches address shortcomings of prior work and provide beneficial explanations to practitioners.
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain, identifying a single, on-manifold change to the input such that the model becomes more certain in its prediction. We broaden the exploration to examine $δ$-CLUE, the set of potential CLUEs within a $δ$ ball of the original input in latent space. We study the diversity of such sets and find that many CLUEs are redundant; as such, we propose DIVerse CLUE ($\nabla$-CLUE), a set of CLUEs which each propose a distinct explanation as to how one can decrease the uncertainty associated with an input. We then further propose GLobal AMortised CLUE (GLAM-CLUE), a distinct and novel method which learns amortised mappings on specific groups of uncertain inputs, taking them and efficiently transforming them in a single function call into inputs for which a model will be certain. Our experiments show that $δ$-CLUE, $\nabla$-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.