Efficient computation of contrastive explanations
With the increasing deployment of machine learning systems in practice, transparency and explainability have become serious issues. Contrastive explanations are considered to be useful and intuitive, in particular when it comes to explaining decisions to lay people, since they mimic the way in which humans explain. Yet, so far, comparably little research has addressed computationally feasible technologies, which allow guarantees on uniqueness and optimality of the explanation and which enable an easy incorporation of additional constraints. Here, we will focus on specific types of models rather than black-box technologies. We study the relation of contrastive and counterfactual explanations and propose mathematical formalizations as well as a 2-phase algorithm for efficiently computing (plausible) pertinent positives of many standard machine learning models.
Code (1)
Tasks
BIG-bench Machine LearningcounterfactualSimilar Papers 제목 키워드 기반
Can You Tell the Difference? Contrastive Explanations for ABox Entailments
We introduce the notion of contrastive ABox explanations to answer questions of the type "Why is a an instance of C, but b is not?". While there are various approaches for explaining positive entailments (why is C(a) ent…
Efficient Contrastive Explanations on Demand
Recent work revealed a tight connection between adversarial robustness and restricted forms of symbolic explanations, namely distance-based (formal) explanations. This connection is significant because it represents a fi…
Adversarial RobustnessAbductive and Contrastive Explanations for Scoring Rules in Voting
We view voting rules as classifiers that assign a winner (a class) to a profile of voters' preferences (an instance). We propose to apply techniques from formal explainability, most notably abductive and contrastive expl…
Why this and not that? A Logic-based Framework for Contrastive Explanations
We define several canonical problems related to contrastive explanations, each answering a question of the form ''Why P but not Q?''. The problems compute causes for both P and Q, explicitly comparing their differences. …
Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations
Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impact…
Adversarial AttackAdversarial RobustnesscounterfactualSentiment Analysis