Delivering Inflated Explanations

• URL: http://arxiv.org/abs/2306.15272v1
• Date: Tue, 27 Jun 2023 07:54:18 GMT
• Title: Delivering Inflated Explanations
• Authors: Yacine Izza, Alexey Ignatiev, Peter Stuckey, Joao Marques-Silva
• Abstract summary: A formal approach to explainability builds a formal model of the AI system. A formal abductive explanation is a set of features, such that if they take the given value will always lead to the same decision. In this paper we define inflated explanations which is a set of features, and for each feature of set of values, such that the decision will remain unchanged.
• Score: 17.646704122091087
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the quest for Explainable Artificial Intelligence (XAI) one of the questions that frequently arises given a decision made by an AI system is, ``why was the decision made in this way?'' Formal approaches to explainability build a formal model of the AI system and use this to reason about the properties of the system. Given a set of feature values for an instance to be explained, and a resulting decision, a formal abductive explanation is a set of features, such that if they take the given value will always lead to the same decision. This explanation is useful, it shows that only some features were used in making the final decision. But it is narrow, it only shows that if the selected features take their given values the decision is unchanged. It's possible that some features may change values and still lead to the same decision. In this paper we formally define inflated explanations which is a set of features, and for each feature of set of values (always including the value of the instance being explained), such that the decision will remain unchanged. Inflated explanations are more informative than abductive explanations since e.g they allow us to see if the exact value of a feature is important, or it could be any nearby value. Overall they allow us to better understand the role of each feature in the decision. We show that we can compute inflated explanations for not that much greater cost than abductive explanations, and that we can extend duality results for abductive explanations also to inflated explanations.

Related papers

• Abductive explanations of classifiers under constraints: Complexity and properties [6.629765271909503]
  We propose three new types of explanations that take into account constraints. They can be generated from the whole feature space or from a dataset. We show that coverage is powerful enough to discard redundant and superfluous AXp's.
  arXiv  Detail & Related papers  (2024-09-18T17:15:39Z)
• Axiomatic Characterisations of Sample-based Explainers [8.397730500554047]
  We scrutinize explainers that generate feature-based explanations from samples or datasets. We identify the entire family of explainers that satisfy two key properties which are compatible with all the others. We introduce the first (broad family of) explainers that guarantee the existence of explanations and irrefutable global consistency.
  arXiv  Detail & Related papers  (2024-08-09T07:10:07Z)
• A New Class of Explanations for Classifiers with Non-Binary Features [11.358487655918676]
  Two types of explanations have been receiving increased attention in the literature when analyzing the decisions made by classifiers. We show that these explanations can be significantly improved in the presence of non-binary features. Necessary and sufficient reasons were also shown to be the prime implicates and implicants of the complete reason for a decision.
  arXiv  Detail & Related papers  (2023-04-28T11:05:46Z)
• Eliminating The Impossible, Whatever Remains Must Be True [46.39428193548396]
  We show how one can apply background knowledge to give more succinct "why" formal explanations. We also show how to use existing rule induction techniques to efficiently extract background information from a dataset.
  arXiv  Detail & Related papers  (2022-06-20T03:18:14Z)
• Explanatory Paradigms in Neural Networks [18.32369721322249]
  We present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to reasoning-based questions. The answers to these questions are observed correlations, observed counterfactuals, and observed contrastive explanations respectively. The term observed refers to the specific case of post-hoc explainability, when an explanatory technique explains the decision $P$ after a trained neural network has made the decision $P$.
  arXiv  Detail & Related papers  (2022-02-24T00:22:11Z)
• Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
  We study saliency-based explanations over textual data. We find that people often mis-interpret the explanations. We propose a method to adjust saliencies based on model estimates of over- and under-perception.
  arXiv  Detail & Related papers  (2022-01-27T15:20:32Z)
• Diagnosing AI Explanation Methods with Folk Concepts of Behavior [70.10183435379162]
  We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. We use folk concepts of behavior as a framework of social attribution by the human explainee.
  arXiv  Detail & Related papers  (2022-01-27T00:19:41Z)
• Are Training Resources Insufficient? Predict First Then Explain! [54.184609286094044]
  We argue that the predict-then-explain (PtE) architecture is a more efficient approach in terms of the modelling perspective. We show that the PtE structure is the most data-efficient approach when explanation data are lacking.
  arXiv  Detail & Related papers  (2021-08-29T07:04:50Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)
• Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach [11.871523410051527]
  We consider an explanation as a set of the system's data inputs that causally drives the decision. We show that features that have a large importance weight for a model prediction may not affect the corresponding decision.
  arXiv  Detail & Related papers  (2020-01-21T09:58:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.