Formal Concept Analysis

Also known as FCA

Formal Concept Analysis (FCA) studies how objects and their attributes form concepts, ordered from specific to general in a concept lattice. Its main tools include closure operators, lattice construction, attribute implications, and extensions for fuzzy, relational, and many-valued data. These structures support interpretable machine-learning representations and counterfactuals, as well as retrieval, knowledge discovery, and analysis of legal or social data. A central challenge is preserving useful structure while ensuring scalability and reliable reasoning when object–attribute data are uncertain, extracted by language models, or iteratively transformed.

Latest papers

12 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity
Sep 17, 2026Abdullahi Isa, Souley Boukari, Muhammad AliyuBreast Cancer Counterfactual Explanations
Department of Computer Science, Faculty of Computing, Abubakar Tafawa Balewa University, Bauchi, Nigeria.
When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Logic
Sep 1, 2026Surya SakaAlgorithmic Auditing Legal Document Analysis
JudicialMind
Convergence issues in Relational Concept Analysis based on AOC-posets
Aug 30, 2026Xavier Dolques, Agnès Braud, Alain Gutierrez +2Formal Concept Analysis
Univ. de Strasbourg, ENGEES, CNRS, ICube UMR 7357, F-67000 Strasbourg, France · LIRMM, Univ. Montpellier, CNRS, Montpellier, France
Formal Concept Analysis with Three Types of Negation
Aug 29, 2026Zhenghua PanFormal Concept Analysis
School of Mathematics and Data Science, Jiangnan University, Wuxi 214122, China
Exploring ESC Winners with Nested Diagrams
Aug 13, 2026Anurag Sharma, Marcel Nöhre, Gerd StummeFormal Concept Analysis Data Visualization
Knowledge & Data Engineering Group (KDE), University of Kassel, Germany · Interdisciplinary Research Center for Information Systems Design (ITeG), University of Kassel, Germany
Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis
Jul 2, 2026Yujin Yang, Heejung LeeKG Construction LLM Grounding
Hanyang University Seoul, Korea
Interpretable Crisis Behavior Analysis Using Mobility and Social Media Data
Jun 8, 2026Muhammad Hamza Arshad Majeed, Sidahmed Benabderrahmane, Talal RahwanSocial Media Analysis Association Rule Mining
New York University (NYUAD), Division of Science, Computer Science Department
A Variability-Based Framework for Interpretable Naming in Formal and Relational Concept Analysis
Jun 7, 2026Alain Gutierrez, Marianne Huchard, Pierre Martin +2Formal Concept Analysis
LIRMM, Univ. Montpellier, CNRS, Montpellier, France. · CIRAD, UPR AIDA, F-34398, Montpellier, France. · AIDA, CIRAD, Univ. Montpellier, Montpellier, France. +1
A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders
Jun 5, 2026Chenhao Zhang, Chris Lin, Su-In LeeSparse Autoencoders Neural Network Interpretability
Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, USA.
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
Jun 3, 2026Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha +2Visual Representation Learning Interpretable ML
IIT Hyderabad · Amazon, India · KLA +1
ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation
May 19, 2026Roman Prosvirnin, Sergei Kuznetsov, Seungmin JinMulti-Hop QA Graph Retrieval-Augmented Generation
HSE University
Factorizing formal contexts from closures of necessity operators
Feb 25, 2026Roberto G. Aragón, Jesús Medina, Eloísa Ramírez-PoussaFormal Concept Analysis Matrix Factorization
Department of Mathematics, University of Cádiz. Spain

Sep 17, 2026J/K move · Enter open · S save

FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity

Abdullahi Isa, Souley Boukari, Muhammad Aliyu

Department of Computer Science, Faculty of Computing, Abubakar Tafawa Balewa University, Bauchi, Nigeria.

Breast Cancer Counterfactual Explanations Formal Concept Analysis Multimodal Model Interpretability

Open paper AskPDF arXiv

Deep learning models for multi-modal breast cancer diagnosis achieve high predictive accuracy but remain clinically unacceptable without actionable, counterfactual explanations. Attribution-based methods (LIME, SHAP) are categorically inapplicable to this purpose, as they generate no alternative instances and thus cannot be evaluated on counterfactual quality metrics. This investigation provides empirical evidence that FCA-Guided Counterfactual (FCA-CF) framework that uses a Formal Concept Analysis (FCA) concept lattice as a hard structural constraint on counterfactual search, operating over a multi-modal TCGA-BRCA dataset. We benchmark against four genuine counterfactual methods: Wachter-style CF, DiCE, FACE, and NICE, evaluated on 60 benign-predicted TCGA-BRCA instances. The FCA-CF framework achieves Validity = 1.0000 (100% of counterfactuals successfully flip the prediction), Sparsity = 2.37 features changed (best among all valid methods), and Proximity = 0.900 (normalised L2-based, matching NICE as joint best). The classifier achieves Accuracy = 0.980, F1 = 0.976, ROC-AUC = 0.9947. Ablation analysis confirms that the FCA lattice constraint is the primary sparsity driver (removing it increases sparsity by +40%, p < 0.001, Cohen's d = 0.78), while Phase C greedy refinement accounts for the largest individual contribution (+113% sparsity increase when disabled, p < 0.001, d = 5.01). FCA-guided counterfactual generation achieves a clinically important Pareto-dominant outcome; it is simultaneously the sparsest and among the most proximate of all valid methods, with perfect validity. The emergent sparsity property arising from lattice topology rather than numerical penalty terms constitutes a structurally novel contribution to the counterfactual explanation literature.