mlsanityData to 14 Oct 2026

Probabilistic Sufficient Explanations

arXiv 2105.10118 ↗First posted 21 May 2021cs.LG cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabilistic sufficient explanations, which formulate explaining an instance of classification as choosing the "simplest" subset of features such that only observing those features is "sufficient" to explain the classification. That is, sufficient to give us strong probabilistic guarantees that the model will behave similarly when all features are observed under the data distribution. In addition, we leverage tractable probabilistic reasoning tools such as probabilistic circuits and expected predictions to design a scalable algorithm for finding the desired explanations while keeping the guarantees intact. Our experiments demonstrate the effectiveness of our algorithm in finding sufficient explanations, and showcase its advantages compared to Anchors and logical explanations.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

18 of 41 references.

References · 18

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  5. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  6. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  7. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  8. 2020On The Reasons Behind Decisionscited by 100
  9. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 57
  10. 2020On Explaining Decision Treescited by 49
  11. 2020On Tractable Representations of Binary Neural Networkscited by 34
  12. 2019On Validating, Repairing and Refining Heuristic ML Explanationscited by 32
6 more
  1. 2019On Tractable Computation of Expected Predictionscited by 19
  2. 2020The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsetscited by 14
  3. 2019Learning Logistic Circuitscited by 12
  4. 2019What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Featurescited by 12
  5. 2020Handling Missing Data in Decision Trees: A Probabilistic Approachcited by 9
  6. 2018On Robust Trimming of Bayesian Network Classifierscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 2; 2024: 4; 2025: 7; 2026: 3.

24 papers.

Sort:

  1. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  2. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  3. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  4. 2022On the Computation of Necessary and Sufficient Explanationscited by 23
  5. 2024Local vs. Global Interpretability: A Computational Complexity Perspectivecited by 23
  6. 2022On Computing Probabilistic Abductive Explanationscited by 18
  7. 2025Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanationscited by 13
  8. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  9. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 11
  10. 2025Probabilistic Stability Guarantees for Feature Attributionscited by 9
  11. 2025Scaling Probabilistic Circuits via Monarch Matricescited by 9
  12. 2022Provably Precise, Succinct and Efficient Explanations for Decision Treescited by 8
12 more
  1. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  2. 2022On Computing Relevant Features for Explaining NBCscited by 5
  3. 2024Even-if Explanations: Formal Foundations, Priorities and Complexitycited by 4
  4. 2024Sufficient and Necessary Explanations (and What Lies in Between)cited by 3
  5. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  6. 2025On Spectral Properties of Gradient-based Explanation Methodscited by 2
  7. 2026Unifying Formal Explanations: A Complexity-Theoretic Perspectivecited by 2
  8. 2022Explainability as statistical inferencecited by 1
  9. 2024Value-Based Rationales Improve Social Experience: A Multiagent Simulation Studycited by 1
  10. 2026Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networkscited by 1
  11. 2023Pruning-Based Extraction of Descriptions from Probabilistic Circuitscited by 0
  12. 2026Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicingcited by 0