Dan Ley
Dan Ley
Publications
Contact
CV
Light
Dark
Automatic
1
GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations
The major shortcoming associated with counterfactual methods is their inability to provide explanations beyond the local or instance-level. We take this opportunity to propose Global & Efficient Counterfactual Explanations (GLOBE-CE), a flexible framework that tackles the reliability and scalability issues associated with current state-of-the-art, particularly on higher dimensional datasets and in the presence of continuous features. Furthermore, we provide a unique mathematical analysis of categorical feature translations, utilising it in our method.
Dan Ley
,
Saumitra Mishra
,
Daniele Magazzeni
Last updated on Jul 8, 2023
PDF
Cite
Poster
Diverse, Global 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 Jul 8, 2023
PDF
Cite
Poster
Cite
×