Open AccessPosted Content
Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
TLDR
The authors performed an LDA topic modeling analysis under a PRISMA framework to find the most relevant literature articles, which resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data.Abstract:
There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.read more
Citations
More filters
Proceedings ArticleDOI
DiCE4EL: Interpreting Process Predictions using a Milestone-Aware Counterfactual Approach
TL;DR: In this paper, the authors explore the use of a popular model-agnostic counterfactual algorithm, DiCE, in the context of predictive process analytics, and propose an approach that supports deriving milestone-aware explanations at key intermediate stages along process execution to promote interpretability.
Posted Content
Convex optimization for actionable \& plausible counterfactual explanations.
André Artelt,Barbara Hammer +1 more
TL;DR: In this paper, a mechanism for ensuring actionability and plausibility of the resulting counterfactual explanations is proposed, based on a convex model of the decision-making process.
Posted Content
Amortized Generation of Sequential Counterfactual Explanations for Black-box Models.
TL;DR: In this article, a stochastic control-based approach is proposed to generate sequential counterfactual explanations (CFEs) that allow the model to move stochastically and sequentially across intermediate states to a final state.
Posted Content
Interpreting Process Predictions using a Milestone-Aware Counterfactual Approach
TL;DR: In this article, the authors explore the use of a recent, model-agnostic counterfactual algorithm, DiCE, in the context of predictive process analytics, and propose an approach that supports deriving milestone-aware counter-factuals at different stages of a trace to promote interpretability.
Posted Content
Pitfalls of Explainable ML: An Industry Perspective.
TL;DR: In this article, the authors enumerate challenges in explainable ML from an industry perspective, and they hope these challenges will serve as promising future research directions, and would contribute to democratizing explainableML.
References
More filters
Book
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
TL;DR: Probabilistic Reasoning in Intelligent Systems as mentioned in this paper is a complete and accessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty, and provides a coherent explication of probability as a language for reasoning with partial belief.
Book ChapterDOI
Visualizing and Understanding Convolutional Networks
Matthew D. Zeiler,Rob Fergus +1 more
TL;DR: A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
MonographDOI
Causality: models, reasoning, and inference
TL;DR: The art and science of cause and effect have been studied in the social sciences for a long time as mentioned in this paper, see, e.g., the theory of inferred causation, causal diagrams and the identification of causal effects.
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Book
A Treatise of Human Nature
TL;DR: Hume's early years and education is described in a treatise of human nature as discussed by the authors. But it is not a complete account of the early years of his life and education.