mlsanityData to 7 Oct 2026

Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning

arXiv 2402.14726 ↗First posted 22 Feb 2024cs.LG cs.AI stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

A problem of incorporating the expert rules into machine learning models for extending the concept-based learning is formulated in the paper. It is proposed how to combine logical rules and neural networks predicting the concept probabilities. The first idea behind the combination is to form constraints for a joint probability distribution over all combinations of concept values to satisfy the expert rules. The second idea is to represent a feasible set of probability distributions in the form of a convex polytope and to use its vertices or faces. We provide several approaches for solving the stated problem and for training neural networks which guarantee that the output probabilities of concepts would not violate the expert rules. The solution of the problem can be viewed as a way for combining the inductive and deductive learning. Expert rules are used in a broader sense when any logical function that connects concepts and class labels or just concepts with each other can be regarded as a rule. This feature significantly expands the class of the proposed results. Numerical examples illustrate the approaches. The code of proposed algorithms is publicly available.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

32 of 42 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  3. 2020Concept Bottleneck Modelscited by 1,022
  4. 2022Post-hoc Concept Bottleneck Modelscited by 289
  5. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  6. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 128
  7. 2021Do Concept Bottleneck Models Learn as Intended?cited by 114
  8. 2023Probabilistic Concept Bottleneck Modelscited by 101
  9. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  10. 2022Interactive Concept Bottleneck Modelscited by 79
  11. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  12. 2023Learning Bottleneck Concepts in Image Classificationcited by 49
20 more
  1. 2023Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Modelscited by 40
  2. 2023Human Uncertainty in Concept-Based AI Systemscited by 39
  3. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  4. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  5. 2023Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosiscited by 26
  6. 2023Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanationscited by 21
  7. 2020Learning Interpretable Concept-Based Models with Human Feedbackcited by 17
  8. 2024Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learningcited by 17
  9. 2022Concept-based Explanations for Out-Of-Distribution Detectorscited by 16
  10. 2023From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networkscited by 13
  11. 2023CLIP-QDA: An Explainable Concept Bottleneck Modelcited by 13
  12. 2023A New Computationally Simple Approach for Implementing Neural Networks with Output Hard Constraintscited by 12
  13. 2020Interpretable Time-series Classification on Few-shot Samplescited by 11
  14. 2023Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitiscited by 11
  15. 2024Do Concept Bottleneck Models Respect Localities?cited by 10
  16. 2023Towards Concept-based Interpretability of Skin Lesion Diagnosis using Vision-Language Modelscited by 9
  17. 2023Transparent Anomaly Detection via Concept-based Explanationscited by 5
  18. 2023CEIR: Concept-based Explainable Image Representation Learningcited by 5
  19. 2022Concept-Based Explanations for Tabular Datacited by 4
  20. 2023Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffscited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Modelscited by 12
  2. 2024FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rulescited by 1
  3. 2025Automated Video-EEG Analysis in Epilepsy Studies: Advances and Challengescited by 0