Кузнецов Сергей Олегович

Introducing the closure structure and the GDPM algorithm for mining and understanding a tabular dataset

2022 · ARTICLE · en

Поиск паттернов является одной из наиболее развитых областей анализа данных. Такие алгоритмы часто содержат много евристик и недостаточно формализовны. В этой статье мы переспатриваем направление поиска паттернов, в частности поиск itemset'ов, позволяющих анализировать бинарные данные и находит осмысленные наборы признаков и ассоциативные правила. В статье описывается специальная структура замыканий на основании замкнутых паттернов и их, так называемых, отмычек. Эта структура определяет паттерны в терминах классов эквивалентностей. Кроме этой теоретический работы в статье вводится и описывает практический алгоритм GDPM для расчёта такой структуры. Особенностью работы этого алгоритма является то, что в качестве результата своей работы он позвляет получить характеристику выборки данных как целого, а не отдельные паттерны. Результаты работы алгоритма проверены на реальных выборках данных.

Human knowledge models: Learning applied knowledge from the data

2022 · ARTICLE · en

Artificial intelligence and machine learning have demonstrated remarkable results in science and applied work. However, present AI models, developed to be run on computers but used in human-driven applications, create a visible disconnect between AI forms of processing and human ways of discovering and using knowledge. In this work, we introduce a new concept of “Human Knowledge Models” (HKMs), designed to reproduce human computational abilities. Departing from a vast body of cognitive research, we formalized the definition of HKMs into a new form of machine learning. Then, by training the models with human processing capabilities, we learned human-like knowledge, that humans can not only understand, but also compute, modify, and apply. We used several datasets from different applied fields to demonstrate the advantages of HKMs, including their high predictive power and resistance to noise and overfitting. Our results proved that HKMs can efficiently mine knowledge directly from the data and can compete with complex AI models in explaining the main data patterns. As a result, our study reveals the great potential of HKMs, particularly in the decision-making applications where “black box” models cannot be accepted. Moreover, this improves our understanding of how well human decision-making, modeled by HKMs, can approach the ideal solutions in real-life problems.

Towards Fast Finding Optimal Short Classifiers

2022 · CHAPTER · en

Studies on Explainable Artificial Intelligence show that a model should be small in order to be human understandable. The restriction on the size of a model drastically reduces the space of possible solutions. Many rule learning models still rely on greedy algorithms for generating ensembles of decision trees. This paper discusses FCA-inspired mathematical and engineering techniques to efficiently find most optimal short binary classifiers, i.e., classifiers that consist of no more than three binary attributes and are optimal w.r.t. F1 score.

Intrinsically Interpretable Document Classification via Concept Lattices

2022 · CHAPTER · en

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 Analysis (FCA) and approaches from applied graph theory. FCA is used to formalize the vague notion of concepts in terms of the formal concepts found in the concept lattices of various document classes. The graph of the lattice covering relation helps to utilize the topological information present in the document-class concept lattices for classifying documents. Finally, the formal concepts that made the strongest contributions to the predictions of the document classifier are revealed, along with their intents; thereby making their contribution more comprehensible to human beings.

lazy classification of underground forums messages using pattern structures

2022 в печати · ARTICLE · en

Underground forums are monitored platforms where hackers announce attacks and tools to carry on attacks on businesses or organizations. In this paper, we will experiment on assessing the risk of a dataset of these messages, using pattern structures and a lazy classification scheme, with some introduced complexity-reducing elements and natural language analysis techniques. The results show promising application for this method for this problem, and serve as an introductory step for deeper investigation

Decision Concept Lattice vs. Decision Trees and Random Forests

2021 · CHAPTER · en

Exploring the dataset structure by means of delta-classes of equivalence. The case of the titanic dataset?

2021 · CHAPTER · en

Summation of Decision Trees

2021 · CHAPTER · en

Ensembles of decision trees, like Random Forests are efficient machine learning models with state-of-the-art prediction quality. However, their predictions are much less transparent than those of a single decision tree. In this paper, we describe a prediction model based on a single decision tree in terms of Formal Concept Analysis. We define a differential way to describing a decision rule. We conclude by presenting an approach to summing an ensemble of decision trees into a single decision semilattice with the same predictions.

Ensemble Techniques for Lazy Classification Based on Pattern Structures

2021 · CHAPTER · en

This paper presents different versions of classification ensemble methods based on pattern structures. Each of these methods is described and tested on multiple datasets (including datasets with exclusively numerical and exclusively nominal features). As a baseline model Random Forest generation is used. For some classification tasks the classification algorithms based on pattern structures showed better performance than Random Forest. The quality of the algorithms is noticeably dependent on ensemble aggregation function and on boosting weighting scheme.

Next Priority Concept: A new and generic algorithm computing concepts from complex and heterogeneous data

2020 · CHAPTER · en

In this article, we present a new data type agnostic algorithm calculating a concept lattice from heterogeneous and complex data. Our NextPriorityConcept algorithm is first introduced and proved in the binary case as an extension of Bordat's algorithm with the notion of strategies to select only some predecessors of each concept, avoiding the generation of unreasonably large lattices. The algorithm is then extended to any type of data in a generic way. It is inspired from pattern structure theory, where data are locally described by predicates independent of their types, allowing the management of heterogeneous data.