arXiv subjects
Publications and source records attributed to Gerd Stumme.
Dimension of partially ordered sets (posets for short) can be seen as a measure of how much space is needed to store posets. Refining the definition of dimension, or actually the local dimension, in this respect we obtain the notion of relative dimension. We discuss properties of relative dimension and we give bounds for relative dimension of some well-known families of posets.
We present ConceptFlow, a scikit-learn-compatible Python library for Formal Concept Analysis that constructs and renders nested line diagrams from many-valued formal contexts. Given a many-valued context and a partition of its attributes into conceptual scales, ConceptFlow performs conceptual scaling, computes the factor lattices, identifies filled nodes of the corresponding subdirect product, and produces an interactive visualization. We apply ConceptFlow to the winners of the Eurovision Song Contest from 1975 to 2025, exploring relationships between voting patterns and musical characteristics. Voting support is captured by an outer scale spanning regional, cultural, historical, and political dimensions, while an inner scale captures musical characteristics via tempo and key. The resulting nested line diagram reveals implications across both scales, exposing dependencies between how winning entries were voted for and the musical properties they share.
We propose a flexible, two-phase algorithm for labeling line diagrams of ordered sets, in which the nodes of direct neighbors in the order relation are connected by a straight, upward-pointing line. In contrast to the labeling of diagrams of arbitrary graphs, we benefit from the fact that all edges in line diagrams of ordered sets are more or less vertical. In this paper, we study the placement of all labels such that they do not intersect with any nodes, lines, or other labels while minimizing the distances between the nodes and their labels. Our approach starts by filtering the fixed-position model using line diagram-specific readability criteria. For labels that cannot be placed adjacent to their node (overflow labels), we exploit the free space in the graph's interior or the infinite space surrounding the drawing and link the labels with their respective node by straight binding lines that should not cross other nodes or labels if possible. To balance quality and runtime, we derive an initial placement of the overflow labels using a cost function over a sparse grid of candidates, followed by a force-based refinement step to fine-tune the layout. Furthermore, we demonstrate the flexibility of this approach by applying it to the visual constraints of line diagrams in the field of Formal Concept Analysis (FCA), where certain labels have to be placed above their node and others below. This special version of the algorithm shows that a pre-filtering in the first phase and minimal adjustments for the cost function and force-based model are sufficient to handle the dual labeling requirements of concept lattices.
The visualization of concept lattices is a central problem in the field of Formal Concept Analysis. Force-directed algorithms, as popular in graph drawing, are a promising approach, treating lattice diagrams as physical models, optimizing node positions based on forces derived from the lattice structure. We build on the work of Zschalig, who, however, limited himself to attribute-additive diagrams. We use a more general additivity, in which both the attributes and the objects contribute to the positions of the concept nodes. We replace the planarity enhancer used by Zschalig to obtain a starting diagram for force-directed optimization with the DimDraw algorithm, which generates structured order diagrams on its own. The combination results in DimFlux, an algorithm that leverages the advantages of DimDraw but generates additive diagrams in which readability is increased by maximizing the conflict distance between nodes and non-incident edges.
Distributivity is a well-established and extensively studied notion in lattice theory. In the context of data analysis, particularly within Formal Concept Analysis (FCA), lattices are often observed to exhibit a high degree of distributivity. However, no standardized measure exists to quantify this property. In this paper, we introduce the notion of rises in (concept) lattices as a means to assess distributivity. Rises capture how the number of attributes or objects in covering concepts change within the concept lattice. We show that a lattice is distributive if and only if no non-unit rises occur. Furthermore, we relate rises to the classical notion of meet- and join distributivity. We observe that concept lattices from real-world data are to a high degree join-distributive, but much less meet-distributive. We additionally study how join-distributivity manifests on the level of ordered sets.
The vast growth of data has rendered traditional manual inspection infeasible, necessitating the adoption of computational methods for efficient data exploration. Topic modeling has emerged as a powerful tool for analyzing large-scale textual datasets, enabling the extraction of latent semantic structures. However, existing methods for topic modeling often struggle to provide interpretable representations that facilitate deeper insights into data structure and content. In this paper, we propose FAT-CAT, an approach based on Formal Concept Analysis (FCA) to enhance meaningful topic aggregation and visualization of discovered topics. Our approach can handle diverse topics and file types -- grouped by directories -- to construct a concept lattice that offers a structured, hierarchical representation of their topic distribution. In a case study on the ETYNTKE dataset, we evaluate the effectiveness of our approach against other representation methods to demonstrate that FCA-based aggregation provides more meaningful and interpretable insights into dataset composition than existing topic modeling techniques.
We introduce the Birkhoff completion as the smallest distributive lattice in which a given finite lattice can be embedded as semi-lattice. We discuss its relationship to implicational theories, in particular to R. Wille's simply-implicational theories. By an example, we show how the Birkhoff completion can be used as a tool for ordinal data science.
With our work, we contribute towards a qualitative analysis of the discourse on controversies in online news media. For this, we employ Formal Concept Analysis and the economics of conventions to derive conceptual controversy maps. In our experiments, we analyze two maps from different news journals with methods from ordinal data science. We show how these methods can be used to assess the diversity, complexity and potential bias of controversies. In addition to that, we discuss how the diagrams of concept lattices can be used to navigate between news articles.
Order is one of the main instruments to measure the relationship between objects in (empirical) data. However, compared to methods that use numerical properties of objects, the amount of ordinal methods developed is rather small. One reason for this is the limited availability of computational resources in the last century that would have been required for ordinal computations. Another reason -- particularly important for this line of research -- is that order-based methods are often seen as too mathematically rigorous for applying them to real-world data. In this paper, we will therefore discuss different means for measuring and 'calculating' with ordinal structures -- a specific class of directed graphs -- and show how to infer knowledge from them. Our aim is to establish Ordinal Data Science as a fundamentally new research agenda. Besides cross-fertilization with other cornerstone machine learning and knowledge representation methods, a broad range of disciplines will benefit from this endeavor, including, psychology, sociology, economics, web science, knowledge engineering, scientometrics.
The investigation of social networks is often hindered by their size as such networks often consist of at least thousands of vertices and edges. Hence, it is of major interest to derive compact structures that represent important connections of the original network. In this work, we derive such structures with orometric methods that are originally designed to identify outstanding mountain peaks and relationships between them. By adapting these methods to social networks, it is possible to derive family trees of important vertices. Our approach consists of two steps. We first apply a novel method for discarding edges that stand for weak connections. This is done such that the connectivity of the network is preserved. Then, we identify the important peaks in the network and the key cols, i.e., the lower points that connect them. This gives us a compact network that displays which peaks are connected through which cols. Thus, a natural hierarchy on the peaks arises by the question which higher peak comes behind the col, yielding to chains of peaks with increasing heights. The resulting line-parent hierarchy displays dominance relations between important vertices. We show that networks with hundreds or thousands of edges can be condensed to a small set of vertices and key connections between them.
Given a formal context, an ordinal factor is a subset of its incidence relation that forms a chain in the concept lattice, i.e., a part of the dataset that corresponds to a linear order. To visualize the data in a formal context, Ganter and Glodeanu proposed a biplot based on two ordinal factors. For the biplot to be useful, it is important that these factors comprise as much data points as possible, i.e., that they cover a large part of the incidence relation. In this work, we investigate such ordinal two-factorizations. First, we investigate for formal contexts that omit ordinal two-factorizations the disjointness of the two factors. Then, we show that deciding on the existence of two-factorizations of a given size is an NP-complete problem which makes computing maximal factorizations computationally expensive. Finally, we provide the algorithm Ord2Factor that allows us to compute large ordinal two-factorizations.
Lattices and their order diagrams are an essential tool for communicating knowledge and insights about data. This is in particular true when applying Formal Concept Analysis. Such representations, however, are difficult to comprehend by untrained users and in general in cases where lattices are large. We tackle this problem by automatically generating textual explanations for lattices using standard scales. Our method is based on the general notion of ordinal motifs in lattices for the special case of standard scales. We show the computational complexity of identifying a small number of standard scales that cover most of the lattice structure. For these, we provide textual explanation templates, which can be applied to any occurrence of a scale in any data domain. These templates are derived using principles from human-computer interaction and allow for a comprehensive textual explanation of lattices. We demonstrate our approach on the spices planner data set, which is a medium sized formal context comprised of fifty-six meals (objects) and thirty-seven spices (attributes). The resulting 531 formal concepts can be covered by means of about 100 standard scales.
Lattices are a commonly used structure for the representation and analysis of relational and ontological knowledge. In particular, the analysis of these requires a decomposition of a large and high-dimensional lattice into a set of understandably large parts. With the present work we propose /ordinal motifs/ as analytical units of meaning. We study these ordinal substructures (or standard scales) through (full) scale-measures of formal contexts from the field of formal concept analysis. We show that the underlying decision problems are NP-complete and provide results on how one can incrementally identify ordinal motifs to save computational effort. Accompanying our theoretical results, we demonstrate how ordinal motifs can be leveraged to retrieve basic meaning from a medium sized ordinal data set.
In large datasets, it is hard to discover and analyze structure. It is thus common to introduce tags or keywords for the items. In applications, such datasets are then filtered based on these tags. Still, even medium-sized datasets with a few tags result in complex and for humans hard-to-navigate systems. In this work, we adopt the method of ordinal factor analysis to address this problem. An ordinal factor arranges a subset of the tags in a linear order based on their underlying structure. A complete ordinal factorization, which consists of such ordinal factors, precisely represents the original dataset. Based on such an ordinal factorization, we provide a way to discover and explain relationships between different items and attributes in the dataset. However, computing even just one ordinal factor of high cardinality is computationally complex. We thus propose the greedy algorithm in this work. This algorithm extracts ordinal factors using already existing fast algorithms developed in formal concept analysis. Then, we leverage to propose a comprehensive way to discover relationships in the dataset. We furthermore introduce a distance measure based on the representation emerging from the ordinal factorization to discover similar items. To evaluate the method, we conduct a case study on different datasets.
This work investigates the factorization of finite lattices to implode selected intervals while preserving the remaining order structure. We examine how complete congruence relations and complete tolerance relations can be utilized for this purpose and answer the question of finding the finest of those relations to implode a given interval in the generated factor lattice. To overcome the limitations of the factorization based on those relations, we introduce a new lattice factorization that enables the imploding of selected disjoint intervals of a finite lattice. To this end, we propose an interval relation that generates this factorization. To obtain lattices rather than arbitrary ordered sets, we restrict this approach to so-called pure intervals. For our study, we will make use of methods from Formal Concept Analysis (FCA). We will also provide a new FCA construction by introducing the enrichment of an incidence relation by a set of intervals in a formal context, to investigate the approach for lattice-generating interval relations on the context side.
Induced bipartite subgraphs of maximal vertex cardinality are an essential concept for the analysis of graphs. Yet, discovering them in large graphs is known to be computationally hard. Therefore, we consider in this work a weaker notion of this problem, where we discard the maximality constraint in favor of inclusion maximality. Thus, we aim to discover locally maximal bipartite subgraphs. For this, we present three heuristic approaches to extract such subgraphs and compare their results to the solutions of the global problem. For the latter, we employ the algorithmic strength of fast SAT-solvers. Our three proposed heuristics are based on a greedy strategy, a simulated annealing approach, and a genetic algorithm, respectively. We evaluate all four algorithms with respect to their time requirement and the vertex cardinality of the discovered bipartite subgraphs on several benchmark datasets
Attribute exploration is a method from Formal Concept Analysis (FCA) that helps a domain expert discover structural dependencies in knowledge domains which can be represented as formal contexts (cross tables of objects and attributes). In this paper we present an extension of attribute exploration that allows for a group of domain experts and explores their shared views. Each expert has their own view of the domain and the views of multiple experts may contain contradicting information.
Steadily growing amounts of information, such as annually published scientific papers, have become so large that they elude an extensive manual analysis. Hence, to maintain an overview, automated methods for the mapping and visualization of knowledge domains are necessary and important, e.g., for scientific decision makers. Of particular interest in this field is the development of research topics of different entities (e.g., scientific authors and venues) over time. However, existing approaches for their analysis are only suitable for single entity types, such as venues, and they often do not capture the research topics or the time dimension in an easily interpretable manner. Hence, we propose a principled approach for \emph{mapping research trajectories}, which is applicable to all kinds of scientific entities that can be represented by sets of published papers. For this, we transfer ideas and principles from the geographic visualization domain, specifically trajectory maps and interactive geographic maps. Our visualizations depict the research topics of entities over time in a straightforward interpr. manner. They can be navigated by the user intuitively and restricted to specific elements of interest. The maps are derived from a corpus of research publications (i.e., titles and abstracts) through a combination of unsupervised machine learning methods. In a practical demonstrator application, we exemplify the proposed approach on a publication corpus from machine learning. We observe that our trajectory visualizations of 30 top machine learning venues and 1000 major authors in this field are well interpretable and are consistent with background knowledge drawn from the entities' publications. Next to producing interactive, interpr. visualizations supporting different kinds of analyses, our computed trajectories are suitable for trajectory mining applications in the future.