Dan Ley
Dan Ley
Publications
Contact
CV
Light
Dark
Automatic
3
Global Counterfactual Explanations: Investigations, Implementations and Improvements
The major shortcoming associated with counterfactual methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.
Dan Ley
,
Saumitra Mishra
,
Daniele Magazzeni
Last updated on Apr 15, 2022
PDF
Cite
Poster
Diverse and Amortised Counterfactual Explanations for Uncertainty Estimates
To interpret uncertainty estimates, we extend recent work that generates multiple Counterfactual Latent Uncertainty Explanations (𝛿-CLUEs), by applying additional constraints for diversity in the optimisation objective (∇-CLUE). We then propose a distinct method for discovering GLobal AMortised CLUEs (GLAM-CLUE) which learns mappings of arbitrary complexity between groups of uncertain and certain groups in a computationally efficient manner.
Dan Ley
,
Umang Bhatt
,
Adrian Weller
Last updated on Apr 8, 2022
PDF
Cite
Poster
δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
To interpret uncertainty estimates, we extend recent work that generates Counterfactual Latent Uncertainty Explanations (CLUEs), to produce a set of plausible CLUEs- multiple, diverse inputs that are within a δ ball of the original input in latent space, all yielding confident predictions.
Dan Ley
,
Umang Bhatt
,
Adrian Weller
Apr 13, 2021
PDF
Cite
Poster
Cite
×