mlsanityData to 13 Oct 2026

On Computing Relevant Features for Explaining NBCs

arXiv 2207.04748 ↗First posted 11 Jul 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This paper investigates the computation of relevant sets for Naive Bayes Classifiers (NBCs), and shows that, in practice, these are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained with NBCs.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 25 of its 62 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

25 of 62 references.

References · 25

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,515
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,055
  3. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,203
  4. 2018A Survey Of Methods For Explaining Black Box Modelscited by 971
  5. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 442
  6. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 344
  7. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  8. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  9. 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
  10. 2019Towards Explainable Artificial Intelligencecited by 106
  11. 2020On The Reasons Behind Decisionscited by 100
  12. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 57
13 more
  1. 2021On Explaining Random Forests with SATcited by 57
  2. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  3. 2020On Explaining Decision Treescited by 49
  4. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  5. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  6. 2021Explanations for Monotonic Classifierscited by 39
  7. 2019Can I Trust the Explainer? Verifying Post-hoc Explanatory Methodscited by 37
  8. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  9. 2021Provably efficient, succinct, and precise explanationscited by 32
  10. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  11. 2021Probabilistic Sufficient Explanationscited by 24
  12. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  13. 2018A Faster FPTAS for #Knapsackcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 2.

5 papers.

  1. 2022Logic-Based Explainability in Machine Learningcited by 48
  2. 2022On Computing Probabilistic Abductive Explanationscited by 18
  3. 2023Delivering Inflated Explanationscited by 16
  4. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  5. 2024Efficient Contrastive Explanations on Demandcited by 1