?
Shapley and Banzhaf Vectors of a Formal Concept
P. 259–271.
Ignatov D. I., Kwuida L.
We propose the usage of two power indices from cooperative game theory and public choice theory for ranking attributes of closed sets, namely intents of formal concepts (or closed itemsets). The introduced indices are related to extensional concept stability and based on counting generators, especially those that contain a selected attribute. The introduction of such indices is motivated by the so-called interpretable machine learning, which supposes that we do not only have the class membership decision of a trained model for a particular object, but also a set of attributes (in the form of JSM-hypotheses or other patterns) along with individual importance of their single attributes (or more complex constituent elements). We characterise computation of Shapley and Banzhaf values of a formal concept in terms of minimal generators and their order filters, provide the reader with their properties important for computation purposes, and show experimental results.
In book
Vol. 2668. , CEUR-WS.org, 2020.
Avdoshin S. M., Pesotskaya E. Y., Информационные технологии 2026 Т. 32 № 4 С. 185–194
With the rapid advancement of artificial intelligence, and deep learning in particular, models have emerged that are capable of delivering highly accurate predictions. However, the internal logic of such models remains difficult to interpret—an issue of critical importance, especially in domains where the correctness of an algorithm directly affects high-stakes decision-making. One promising avenue for ...
Added: May 8, 2026
Avdoshin S. M., Pesotskaya E. Y., Business Informatics 2026 Vol. 20 No. 1 P. 7–28
The rapid development of artificial intelligence (AI) is accompanied by increasing computational
complexity and decreasing model transparency, which significantly limits its adoption in critical
domains that require a high level of trust, interpretability, and justification of decisions. Under these
conditions, the field of Explainable Artificial Intelligence (XAI) has gained particular importance as it
focuses on approaches and technologies that ...
Added: May 8, 2026
Glushko A., Neznanov A., В кн.: Перспективные материалы и технологии (ПМТ-2024) : Сборник докладов Международной научно-технической конференции ИПТИП РТУ МИРЭА, Москва, 12–16 апреля 2024 годаТ. 1.: М.: РТУ МИРЭА, 2024. С. 380–385.
In this paper we would like to discuss the basic principles, design decisions and tools that formed the basis of a software system for analyzing the results of real experiments and performing computational experiments in chemistry and materials science. With this work we aim to formalize knowledge at multiple levels and improving the efficiency of ...
Added: April 29, 2026
Glushko A., Neznanov A., В кн.: Перспективные материалы и технологии (ПМТ-2025) : Сборник докладов Национальной научно-технической конференции с международным участием, Москва, 07–12 апреля 2025 года.: М.: РТУ МИРЭА, 2025. С. 651–657.
Most of scientific research involves the use of computational tools, while researchers have low IT competences. The efficiency of working with computational modules for scientific research can be significantly increased by guaranteeing reproducibility, interactivity, and reusability of producing artifacts. This can be achieved by using a reactive environment with a standardized set of UI controls, ...
Added: April 29, 2026
Suvorova A., В кн.: XXII национальная конференция по искусственному интеллекту с международным участием (КИИ-2025)Т. 1.: СПб.: Санкт-Петербургский Федеральный исследовательский центр РАН, 2025. С. 310–318.
В работе исследуется проблема чрезмерного полагания (overreliance) пользователей на результаты интерпретации моделей машинного обучения, а также способов ее решения с помощью пояснений, генерируемых большими языковыми моделями (LLM). Результаты эксперимента показали, что большинство моделей, так же как и пользователи-люди в исходном эксперименте, игнорировали аномалии или предлагали правдоподобные, но ложные объяснения, рационализируя выводы. Это указывает на риски ...
Added: February 15, 2026
Sadeghi Z., Alizadehsani R., Cifci M. A. et al., Computers and Electrical Engineering 2024 Vol. 118 No. A Article 109370
Explainable Artificial Intelligence (XAI) encompasses the strategies and methodologies used in constructing AI systems that enable end-users to comprehend and interpret the outputs and predictions made by AI models. The increasing deployment of opaque AI applications in high-stakes fields, particularly healthcare, has amplified the need for clarity and explainability. This stems from the potential high-impact ...
Added: June 8, 2024
Sergei O. Kuznetsov, Parakal E. G., Lecture Notes in Networks and Systems 2023 Vol. 776 P. 423–434
Inherently explainable Machine Learning (ML) models are able to provide explanations for their predictions by virtue of their construction. The explanations of a ML model are more comprehensible if they are expressed in terms of its input features. Our paper proposes an inherently explainable pipeline for document classification using pattern structures and Abstract Meaning Representation ...
Added: February 5, 2024
Shalileh S., Koptseva A., Shishkovskaya T. et al., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2023 Т. 514 № 2 С. 242–249
This paper represents our research to (i) propose an artificial intelligence, AI-based solution to identify depression and (ii) investigate our psychiatric knowledge. Concerning the first objective, we collected and annotated a new audio data set, and scrutinized the performance of eight regression approaches. Our studies showed that k-nearest neighbor and random forest form the group ...
Added: February 2, 2024
Baklanova V., Kurkin A., Teplova T., China Finance Review International 2024 Vol. 14 No. 3 P. 522–548
Purpose – The primary objective of this research is to provide a precise interpretation of the constructed
machine learning model and produce definitive summaries that can evaluate the influence of investor sentiment on the overall sales of non-fungible token (NFT) assets. To achieve this objective, the NFT hype
index was constructed as well as several approaches of ...
Added: December 10, 2023
Magai German, Soroka A., , in: Advances in Neural Computation, Machine Learning, and Cognitive Research VIIVol. 1120.: Studies in Computational Intelligence, 2023.
The basis of transfer learning methods is the ability of deep neural networks to use knowledge from one domain to learn in another domain. However, another important task is the analysis and explanation of the internal representations of deep neural networks models in the process of transfer learning. Some deep models are known to be ...
Added: October 29, 2023
Tamara Teplova, Tatiana Sokolova, David Kissa, Resources Policy 2023 Vol. 86 No. B Article 104253
The purpose of the paper is to reveal the impact of different environment, social, and corporate governance (ESG) indicators on stock liquidity in the emerging Russian market, which is heavily dominated by the natural resources sector. We first apply Explainable Artificial Intelligence (AI) to identify and rank determining factors for stock liquidity on a sample ...
Added: October 23, 2023
Dudyrev E., Kuznetsov S., Napoli A., , in: FCA4AI 2023 What can FCA do for Artificial Intelligence 2023 Proceedings of the 11th International Workshop "What can FCA do for Artificial Intelligence?" co-located with the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) Macao, S.A.R. China; August 20, 2023Vol. 3489.: CEUR-WS.org, 2023. P. 69–80.
Rule Learning and Formal Concept Analysis (FCA) are two fields of science that study similar topic yet speak in a very different terms. This paper describes rule-based machine learning models with FCA-based terminology which results in decision quiver model. A decision quiver, discussed in the paper, is a supervised machine learning model that is based ...
Added: October 4, 2023
Dudyrev E., Kuznetsov S., Napoli A., , in: 17th International Conference, ICFCA 2023, Kassel, Germany, July 17–21, 2023, Proceedings. Formal Concept Analysis, (LNCS, volume 13934).: Switzerland: Springer, 2023. P. 127–142.
In this paper we introduce and study description quivers as compact representations of concept lattices and respective ensembles of decision trees. Formally, description quivers are directed multigraphs where vertices represent concept intents and (multiple) edges represent generators of intents. We study some properties of description quivers and shed light on their use for describing state-of-the-art symbolic machine ...
Added: October 4, 2023
Parakal E. G., Kuznetsov S., , in: Proceedings of the 10th International Workshop "What can FCA do for Artificial Intelligence?"Vol. 3233.: CEUR Workshop Proceedings, 2022. Ch. 2 P. 9–22.
Explanations for the predictions made by Machine Learning (ML) models are best framed in terms of
abstract, high-level concepts that are easily comprehensible to human beings. The use of such concepts
constitutes a subfield of interpretability methods known as concept-based explanations. This work uses
concept-based explanations to build an intrinsically interpretable document classifier using a combination
of Formal Concept ...
Added: May 17, 2023
Jin S., Lee H., Park C. et al., IEEE Transactions on Visualization and Computer Graphics 2023 Vol. 29 No. 1 P. 1102–1112
With deep learning (DL) outperforming conventional methods for different tasks, much effort has been devoted to utilizing DL in various domains. Researchers and developers in the traffic domain have also designed and improved DL models for forecasting tasks such as estimation of traffic speed and time of arrival. However, there exist many challenges in analyzing ...
Added: May 17, 2023
Suvorova A., Смирнова А. В., В кн.: Интегрированные модели и мягкие вычисления в искусственном интеллекте ИММВ-2022. Сборник научных трудов XI Международной научно-практической конференции. В 2-х томах, том 1Т. 1.: Универсум, 2022. С. 247–257.
Interpretable Machine Learning (IML) methods provide valuable insights into model behaviour, but due to variety of available interpretation tools, the particular solution can be not the optimal fit to the needs of the target users. To support decision making in model building and exploration, we propose a modular framework for algorithm selection. The framework is ...
Added: March 17, 2023
Ignatov D. I., Kwuida L., Annals of Mathematics and Artificial Intelligence 2022 Vol. 90 No. 11 P. 1197–1222
We propose the usage of two power indices from cooperative game theory and public choice theory for ranking attributes of closed sets, namely intents of formal concepts (or closed itemsets). The introduced indices are related to extensional concept stability and are also based on counting of generators, especially of those that contain a selected attribute. ...
Added: January 31, 2023