Portal de Periódicos da CAPES

Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates

2022; Association for the Advancement of Artificial Intelligence; Volume: 36; Issue: 7 Linguagem: Inglês

10.1609/aaai.v36i7.20702

2374-3468

Dan Ley, Umang Bhatt, Adrian Weller,

Adversarial Robustness in Machine Learning

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. 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 (∇-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, novel method which learns amortised mappings that apply to 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, ∇-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.