FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rules
Not on the map. Why?
Abstract (arXiv)
A method for solving concept-based learning (CBL) problem is proposed. The main idea behind the method is to divide each concept-annotated image into patches, to transform the patches into embeddings by using an autoencoder, and to cluster the embeddings assuming that each cluster will mainly contain embeddings of patches with certain concepts. To find concepts of a new image, the method implements the frequentist inference by computing prior and posterior probabilities of concepts based on rates of patches from images with certain values of the concepts. Therefore, the proposed method is called the Frequentist Inference CBL (FI-CBL). FI-CBL allows us to incorporate the expert rules in the form of logic functions into the inference procedure. An idea behind the incorporation is to update prior and conditional probabilities of concepts to satisfy the rules. The method is transparent because it has an explicit sequence of probabilistic calculations and a clear frequency interpretation. Numerical experiments show that FI-CBL outperforms the concept bottleneck model in cases when the number of training data is small. The code of proposed algorithms is publicly available.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 28 Jun 2024.
Builds on
38 of 60 references.
References · 38
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2020Concept Bottleneck Modelscited by 1,032
- 2022Post-hoc Concept Bottleneck Modelscited by 293
- 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
- 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
- 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
- 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
- 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
- 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
- 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 131
26 more
- 2021Do Concept Bottleneck Models Learn as Intended?cited by 116
- 2023Probabilistic Concept Bottleneck Modelscited by 101
- 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
- 2018Grounding Visual Explanationscited by 93
- 2022Interactive Concept Bottleneck Modelscited by 79
- 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
- 2023Learning Bottleneck Concepts in Image Classificationcited by 49
- 2023Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Modelscited by 40
- 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
- 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
- 2023Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosiscited by 26
- 2023Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanationscited by 22
- 2020Learning Interpretable Concept-Based Models with Human Feedbackcited by 17
- 2024Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learningcited by 17
- 2022Concept-based Explanations for Out-Of-Distribution Detectorscited by 16
- 2023From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networkscited by 13
- 2023CLIP-QDA: An Explainable Concept Bottleneck Modelcited by 13
- 2020Interpretable Time-series Classification on Few-shot Samplescited by 12
- 2023Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitiscited by 11
- 2024A survey on Concept-based Approaches For Model Improvementcited by 8
- 2022Perspectives on Incorporating Expert Feedback into Model Updatescited by 7
- 2023Transparent Anomaly Detection via Concept-based Explanationscited by 5
- 2023CEIR: Concept-based Explainable Image Representation Learningcited by 5
- 2022Concept-Based Explanations for Tabular Datacited by 4
- 2023Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffscited by 4
- 2024Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learningcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.