On Computing Probabilistic Abductive Explanations

• URL: http://arxiv.org/abs/2212.05990v1
• Date: Mon, 12 Dec 2022 15:47:10 GMT
• Title: On Computing Probabilistic Abductive Explanations
• Authors: Yacine Izza, Xuanxiang Huang, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper and Joao Marques-Silva
• Abstract summary: The most widely studied explainable AI (XAI) approaches are unsound. PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. This paper investigates practical approaches for computing relevant sets for a number of widely used classifiers.
• Score: 30.325691263226968
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\delta}, a set S of features is {\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.

Related papers

• Bisimulation Learning [55.859538562698496]
  We compute finite bisimulations of state transition systems with large, possibly infinite state space. Our technique yields faster verification results than alternative state-of-the-art tools in practice.
  arXiv  Detail & Related papers  (2024-05-24T17:11:27Z)
• Understanding and Mitigating Classification Errors Through Interpretable Token Patterns [58.91023283103762]
  Characterizing errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors. We propose to discover those patterns of tokens that distinguish correct and erroneous predictions. We show that our method, Premise, performs well in practice.
  arXiv  Detail & Related papers  (2023-11-18T00:24:26Z)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• Feature Necessity & Relevancy in ML Classifier Explanations [5.232306238197686]
  Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. It is also critical to understand whether sensitive features can occur in some explanation, or whether a non-interesting feature must occur in all explanations.
  arXiv  Detail & Related papers  (2022-10-27T12:12:45Z)
• On Computing Relevant Features for Explaining NBCs [5.71097144710995]
  It is the case that modelagnostic explainable AI (XAI) can produce incorrect explanations. PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. This paper investigates the complexity of computing sets of relevant features for Naive Bayes classifiers (NBCs) and shows that, in practice, these are easy to compute.
  arXiv  Detail & Related papers  (2022-07-11T10:12:46Z)
• Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles [50.81061839052459]
  We formalize the generation of robust counterfactual explanations as a probabilistic problem. We show the link between the robustness of ensemble models and the robustness of base learners. Our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations.
  arXiv  Detail & Related papers  (2022-05-27T17:28:54Z)
• On Deciding Feature Membership in Explanations of SDD & Related Classifiers [0.685316573653194]
  The paper shows that the feature membership problem (FMP) is hard for $SigmaP$ for a broad class of classifiers. The paper proposes propositional encodings for classifiers represented with Sentential Decision Diagrams (SDDs) and for other propositional languages.
  arXiv  Detail & Related papers  (2022-02-15T16:38:53Z)
• Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals [72.00815192668193]
  Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
  arXiv  Detail & Related papers  (2021-06-01T20:36:48Z)
• Efficient Explanations With Relevant Sets [30.296628060841645]
  This paper investigates solutions for tackling the practical limitations of $delta$-relevant sets. The computation of the subset of $delta$-relevant sets is in NP, and can be solved with a number of calls to an NP oracle.
  arXiv  Detail & Related papers  (2021-06-01T14:57:58Z)
• Discrete Reasoning Templates for Natural Language Understanding [79.07883990966077]
  We present an approach that reasons about complex questions by decomposing them to simpler subquestions. We derive the final answer according to instructions in a predefined reasoning template. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision.
  arXiv  Detail & Related papers  (2021-04-05T18:56:56Z)
• Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms [0.0]
  We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classification. This has become a topic of recent interest as a way to query a trained model and suggest possible actions to overturn its decision.
  arXiv  Detail & Related papers  (2021-03-01T16:04:33Z)

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.