apply formal concept analysis

Relational Concept Analysis (RCA) suffers from non-unique solutions and ambiguous semantic foundations when applied to cyclically dependent data. Method: This paper reconstructs RCA’s formal semantics by characterizing all admissible solutions as common fixed points of a pair of expansion and contraction operators. It integrates Formal Concept Analysis, Description Logic, fixed-point theory, and lattice theory to establish a precise, function-based semantic framework. Contribution/Results: We prove that the solution set forms a complete sublattice of the concept lattice, and identify a dual structure between the minimal solution—corresponding to the standard RCA output—and the maximal solution. This work clarifies RCA’s operational semantics and reveals the algebraic structure of its solution space, thereby providing a rigorous theoretical foundation for robust knowledge discovery and ontology learning.

This study addresses the challenge of balancing efficiency and interpretability in nominal data classification by proposing a novel approach grounded in Formal Concept Analysis (FCA). The method leverages closure operators to identify and retain only those concepts corresponding to Top-Pertinent attributes—i.e., attributes most relevant to the classification task—thereby constructing a lightweight partial concept lattice. This strategy substantially reduces the structural complexity of the lattice while preserving semantic interpretability. Experimental results across multiple datasets demonstrate that the proposed approach outperforms existing FCA-based baselines, achieving a superior trade-off between classification performance and model interpretability.

This study addresses the lack of verifiability and consistency in knowledge generated by language models by proposing a novel approach that integrates Formal Concept Analysis (FCA) with a retrieval-augmented small language model (SLM). For the first time, FCA is embedded into the SLM knowledge construction pipeline as a symbolic verification mechanism, enabling traceable and auditable knowledge expansion through entailment validation, counterexample generation, consistency checking, and attribute suggestion. Experiments on a rare ataxia dataset yield relation F1 scores ranging from 0.29 to 0.52 and entailment F1 scores from 0.22 to 0.30 across ten random seeds. Expanding the seed set substantially increases both the quantity and performance of entailment evaluations, while ablation studies confirm that retrieval-based instance judgment critically contributes to entailment scoring.

This study addresses the challenge that concepts generated by Formal Concept Analysis (FCA) and Relational Concept Analysis (RCA) often rely on technical labels lacking human-interpretable semantic names, thereby hindering domain experts’ understanding and reuse of knowledge. To overcome this limitation, the work proposes a configurable framework that models concept naming as a controlled variability problem, integrating variability modeling with large language models (LLMs). By explicitly governing the exposure of multi-source semantic cues—such as intent, extent, inheritance, and neighboring concepts—the framework generates interpretable names that simultaneously capture intensional meaning and relational context. Empirical evaluation on a pizza restaurant relational dataset demonstrates that the approach produces diverse, semantically coherent concept names, effectively supporting concept interpretation, knowledge validation, and diagnostic assessment of symbolic data quality.

This work addresses the challenge of realizing symbolic conceptual hierarchies and logical reasoning within the continuous embedding space of large language models. It proposes the "lattice representation hypothesis," introducing formal concept analysis into the study of language model representations for the first time. By constructing concept lattices through intersections of half-spaces induced by linear attribute directions, the approach unifies formal concept analysis with the linear representation hypothesis. This framework enables symbolic reasoning via geometric meet (intersection) and join (union) operations. Experiments on WordNet sub-hierarchies demonstrate that the embedding space indeed encodes interpretable concept lattice structures, thereby establishing a principled bridge between continuous geometric representations and symbolic abstraction.

This study addresses the longstanding trade-off between predictive accuracy and interpretability in tree-based models (e.g., decision trees, random forests). Methodologically, it introduces a novel framework that integrates negation-aware association rules: (1) high-confidence, generalizable rules are mined from training data via an enhanced association rule mining algorithm; (2) these rules are encoded as auxiliary features or logical constraints and incorporated into the tree learning process; and (3) a first-order logic–based abductive reasoning mechanism is developed to generate concise, generalizable explanations covering multiple instances. The key contribution lies in the first systematic use of association rules—particularly those containing negative items—to simultaneously enhance both classification accuracy and explanation universality of tree models. Experiments on multiple benchmark datasets demonstrate statistically significant improvements in classification accuracy, a >40% reduction in average explanation length, and markedly increased cross-instance applicability of generated explanations.

This study clarifies the theoretical origins of the eight possibility operators introduced by Dubois and Prade within formal concept analysis and elucidates their relationship to formal concepts. By leveraging Kan extensions from category theory, the paper provides the first unified interpretation of these operators as natural outcomes of Kan extensions derived from an underlying Boolean profunctor, while systematically constructing their dualities and closure structures. The main contributions include proving that NΠ-pairs correspond precisely to formal concepts of the complementary context, characterizing the unique combinations—symmetric or asymmetric—of possibility operators capable of generating formal concepts, and introducing novel closure operators based on these possibility operators, for which completeness and uniqueness in formal concept generation are rigorously established.

This work addresses the lack of causal interpretability in black-box AI models by proposing a causal concept-driven explainable AI framework. The method employs post-hoc semantic concept extraction, constructs a causal graph between concepts and model outputs, and quantifies the effect of concept interventions on predictions via probabilistic sufficiency analysis—yielding faithful explanations with both local and global perspectives. Its key innovation lies in explicitly modeling the causal effects of concept interventions, ensuring explanations are both human-intelligible (high comprehensibility) and strictly consistent with the original model’s behavior (low fidelity loss). Experiments on CelebA demonstrate that the generated concept-based explanations exhibit clear semantics, strong readability, and classification performance highly aligned with the original model, empirically validating the framework’s effective balance between fidelity and interpretability.

This work addresses the redundancy problem in interpretable clustering, where distinct k-relaxed frequent patterns (k-RFPs) yield identical k-covers. The study formally characterizes, for the first time, the theoretical conditions underlying this redundancy and introduces a pattern reduction framework that retains only one representative k-RFP per unique k-cover, substantially compressing the search space. The proposed method integrates a SAT solver to generate candidate patterns, employs integer linear programming (ILP) for cluster selection, and incorporates a filtering mechanism to eliminate redundant patterns. Experimental results on multiple real-world datasets demonstrate that this strategy significantly improves computational efficiency and, in certain scenarios, further enhances clustering quality while preserving the interpretability and robustness of the selected patterns.