A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

Abstract

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

“…Another approach is Contrastive and Counterfactual (C&C) explanations that justify why the output of the algorithms is not any different from what it is and how it could be changed, respectively. [96] examined the theoretical foundation for C&C explanations and reported the state-of-the-art computation frameworks for generating the C&C explanations and identified the shortcomings which can be a topic of future research.…”

Counterfactual Explanations as Interventions in Latent Space

“…Indeed, people usually do not ask why a certain prediction was made, but why this prediction was made instead of another prediction: therefore, one of the usual requirements for a "good" explanation is precisely to be contrastive (Lipton, 1990;Molnar, 2019). Notice that counterfactual explanations have the additional characteristic of representing a conditional clause ("If X were to occur, then Y would (or might) occur") (Stepin et al, 2021), thus adding a "causality layer" on the contrastive statement. Indeed both the work of Karimi et al (2020c) and our proposed methodology present a bridge between "counterfactuals" as intended by causal inference frameworks (Pearl et al, 2016;Spirtes et al, 2000) and "counterfactual explanations" that are usually not embedded in formal causal theory frameworks.…”

“…Since the first proposal of counterfactual explanations by Wachter et al (2017), a large body of research concerning different algorithms and techniques to generate contrastive and counterfactual explanations have been conducted (Verma et al, 2020;Stepin et al, 2021). Most of generation techniques relies on establishing an optimization problem to find the nearest counterfactual in the space of features, with respect to the observation to be explained (Wachter et al, 2017;Karimi et al, 2020a;Mohammadi et al, 2020).…”

“…The volume of research on counterfactual explanations is growing and different solutions have been proposed (refer to Verma et al (2020); Stepin et al (2021) for surveys on counterfactual explanations methods). While these efforts are significant, generally they fall short of generating feasible actions that end users should carry out (Barocas et al, 2020), which is the focus of this work.…”

On the Rationality of Explanations in Classification Algorithms

“…In contrast, we find contrastive and counterfactual explanations. The conceptual similarity between these two last kinds of explanations motivates us to present them together (see [32] for a detailed introduction to contrastiveness and counterfactuals).…”