arXiv subjects

Gerd Stumme

Publications and source records attributed to Gerd Stumme.

At least 37 records · Page 2Linked to original sources

arXiv2021

Towards Explainable Scientific Venue Recommendations

Selecting the best scientific venue (i.e., conference/journal) for the submission of a research article constitutes a multifaceted challenge. Important aspects to consider are the suitability of research topics, a venue's prestige, and the probability of acceptance. The selection problem is exacerbated through the continuous emergence of additional venues. Previously proposed approaches for supporting authors in this process rely on complex recommender systems, e.g., based on Word2Vec or TextCNN. These, however, often elude an explanation for their recommendations. In this work, we propose an unsophisticated method that advances the state-of-the-art in two aspects: First, we enhance the interpretability of recommendations through non-negative matrix factorization based topic models; Second, we surprisingly can obtain competitive recommendation performance while using simpler learning methods.

cs.IR↗

arXiv2021

LG4AV: Combining Language Models and Graph Neural Networks for Author Verification

The automatic verification of document authorships is important in various settings. Researchers are for example judged and compared by the amount and impact of their publications and public figures are confronted by their posts on social media platforms. Therefore, it is important that authorship information in frequently used web services and platforms is correct. The question whether a given document is written by a given author is commonly referred to as authorship verification (AV). While AV is a widely investigated problem in general, only few works consider settings where the documents are short and written in a rather uniform style. This makes most approaches unpractical for online databases and knowledge graphs in the scholarly domain. Here, authorships of scientific publications have to be verified, often with just abstracts and titles available. To this point, we present our novel approach LG4AV which combines language models and graph neural networks for authorship verification. By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style is, at least to some extent, standardized. By the incorporation of a graph neural network structure, our model can benefit from relations between authors that are meaningful with respect to the verification process. For example, scientific authors are more likely to write about topics that are addressed by their co-authors and twitter users tend to post about the same subjects as people they follow. We experimentally evaluate our model and study to which extent the inclusion of co-authorships enhances verification decisions in bibliometric environments.

cs.LG↗

arXiv2021

Attribute Selection using Contranominal Scales

Formal Concept Analysis (FCA) allows to analyze binary data by deriving concepts and ordering them in lattices. One of the main goals of FCA is to enable humans to comprehend the information that is encapsulated in the data; however, the large size of concept lattices is a limiting factor for the feasibility of understanding the underlying structural properties. The size of such a lattice depends on the number of subcontexts in the corresponding formal context that are isomorphic to a contranominal scale of high dimension. In this work, we propose the algorithm ContraFinder that enables the computation of all contranominal scales of a given formal context. Leveraging this algorithm, we introduce delta-adjusting, a novel approach in order to decrease the number of contranominal scales in a formal context by the selection of an appropriate attribute subset. We demonstrate that delta-adjusting a context reduces the size of the hereby emerging sub-semilattice and that the implication set is restricted to meaningful implications. This is evaluated with respect to its associated knowledge by means of a classification task. Hence, our proposed technique strongly improves understandability while preserving important conceptual structures.

cs.AI↗

arXiv2021

Topological Indoor Mapping through WiFi Signals

The ubiquitous presence of WiFi access points and mobile devices capable of measuring WiFi signal strengths allow for real-world applications in indoor localization and mapping. In particular, no additional infrastructure is required. Previous approaches in this field were, however, often hindered by problems such as effortful map-building processes, changing environments and hardware differences. We tackle these problems focussing on topological maps. These represent discrete locations, such as rooms, and their relations, e.g., distances and transition frequencies. In our unsupervised method, we employ WiFi signal strength distributions, dimension reduction and clustering. It can be used in settings where users carry mobile devices and follow their normal routine. We aim for applications in short-lived indoor events such as conferences.

cs.NI↗

arXiv2021

Topic Space Trajectories: A case study on machine learning literature

The annual number of publications at scientific venues, for example, conferences and journals, is growing quickly. Hence, even for researchers it becomes harder and harder to keep track of research topics and their progress. In this task, researchers can be supported by automated publication analysis. Yet, many such methods result in uninterpretable, purely numerical representations. As an attempt to support human analysts, we present topic space trajectories, a structure that allows for the comprehensible tracking of research topics. We demonstrate how these trajectories can be interpreted based on eight different analysis approaches. To obtain comprehensible results, we employ non-negative matrix factorization as well as suitable visualization techniques. We show the applicability of our approach on a publication corpus spanning 50 years of machine learning research from 32 publication venues. Our novel analysis method may be employed for paper classification, for the prediction of future research topics, and for the recommendation of fitting conferences and journals for submitting unpublished work.

cs.LG↗

arXiv2021

Boolean Substructures in Formal Concept Analysis

It is known that a (concept) lattice contains an n-dimensional Boolean suborder if and only if the context contains an n-dimensional contra-nominal scale as subcontext. In this work, we investigate more closely the interplay between the Boolean subcontexts of a given finite context and the Boolean suborders of its concept lattice. To this end, we define mappings from the set of subcontexts of a context to the set of suborders of its concept lattice and vice versa and study their structural properties. In addition, we introduce closed-subcontexts as an extension of closed relations to investigate the set of all sublattices of a given lattice.

cs.DM↗

arXiv2021

Force-Directed Layout of Order Diagrams using Dimensional Reduction

Order diagrams allow human analysts to understand and analyze structural properties of ordered data. While an experienced expert can create easily readable order diagrams, the automatic generation of those remains a hard task. In this work, we adapt force-directed approaches, which are known to generate aesthetically-pleasing drawings of graphs, to the realm of order diagrams. Our algorithm ReDraw thereby embeds the order in a high dimension and then iteratively reduces the dimension until a two-dimensional drawing is achieved. To improve aesthetics, this reduction is equipped with two force-directed steps where one optimizes on distances of nodes and the other on distances of lines in order to satisfy a set of a priori fixed conditions. By respecting an invariant about the vertical position of the elements in each step of our algorithm we ensure that the resulting drawings satisfy all necessary properties of order diagrams. Finally, we present the results of a user study to demonstrate that our algorithm outperforms comparable approaches on drawings of lattices with a high degree of distributivity.

cs.CG↗

arXiv2021

Triadic Exploration and Exploration with Multiple Experts

Formal Concept Analysis (FCA) provides a method called attribute exploration which helps a domain expert discover structural dependencies in knowledge domains that can be represented by a formal context (a cross table of objects and attributes). Triadic Concept Analysis is an extension of FCA that incorporates the notion of conditions. Many extensions and variants of attribute exploration have been studied but only few attempts at incorporating multiple experts have been made. In this paper we present triadic exploration based on Triadic Concept Analysis to explore conditional attribute implications in a triadic domain. We then adapt this approach to formulate attribute exploration with multiple experts that have different views on a domain.

cs.AI↗

arXiv2020

Intrinsic Dimension of Geometric Data Sets

The curse of dimensionality is a phenomenon frequently observed in machine learning (ML) and knowledge discovery (KD). There is a large body of literature investigating its origin and impact, using methods from mathematics as well as from computer science. Among the mathematical insights into data dimensionality, there is an intimate link between the dimension curse and the phenomenon of measure concentration, which makes the former accessible to methods of geometric analysis. The present work provides a comprehensive study of the intrinsic geometry of a data set, based on Gromov's metric measure geometry and Pestov's axiomatic approach to intrinsic dimension. In detail, we define a concept of geometric data set and introduce a metric as well as a partial order on the set of isomorphism classes of such data sets. Based on these objects, we propose and investigate an axiomatic approach to the intrinsic dimension of geometric data sets and establish a concrete dimension function with the desired properties. Our model for data sets and their intrinsic dimension is computationally feasible and, moreover, adaptable to specific ML/KD-algorithms, as illustrated by various experiments.

cs.AI↗

arXiv2020

Interactive Collaborative Exploration using Incomplete Contexts

A well-known knowledge acquisition method in the field of Formal Concept Analysis (FCA) is attribute exploration. It is used to reveal dependencies in a set of attributes with help of a domain expert. In most applications no single expert is capable (time- and knowledge-wise) of exploring the knowledge domain alone. However, there is up to now no theory that models the interaction of multiple experts for the task of attribute exploration with incomplete knowledge. To this end, we to develop a theoretical framework that allows multiple experts to explore domains together. We use a representation of incomplete knowledge as three-valued contexts. We then adapt the corresponding version of attribute exploration to fit the setting of multiple experts. We suggest formalizations for key components like expert knowledge, interaction and collaboration strategy. In particular, we define an order that allows to compare the results of different exploration strategies on the same task with respect to their information completeness. Furthermore we discuss other ways of comparing collaboration strategies and suggest avenues for future research.

cs.AI↗

arXiv2019

Orometric Methods in Bounded Metric Data

A large amount of data accommodated in knowledge graphs (KG) is actually metric. For example, the Wikidata KG contains a plenitude of metric facts about geographic entities like cities, chemical compounds or celestial objects. In this paper, we propose a novel approach that transfers orometric (topographic) measures to bounded metric spaces. While these methods were originally designed to identify relevant mountain peaks on the surface of the earth, we demonstrate a notion to use them for metric data sets in general. Notably, metric sets of items inclosed in knowledge graphs. Based on this we present a method for identifying outstanding items using the transferred valuations functions 'isolation' and 'prominence'. Building up on this we imagine an item recommendation process. To demonstrate the relevance of the novel valuations for such processes we use item sets from the Wikidata knowledge graph. We then evaluate the usefulness of 'isolation' and 'prominence' empirically in a supervised machine learning setting. In particular, we find structurally relevant items in the geographic population distributions of Germany and France.

cs.AI↗

arXiv2019

Drawing Order Diagrams Through Two-Dimension Extension

Order diagrams are an important tool to visualize the complex structure of ordered sets. Favorable drawings of order diagrams, i.e., easily readable for humans, are hard to come by, even for small ordered sets. Many attempts were made to transfer classical graph drawing approaches to order diagrams. Although these methods produce satisfying results for some ordered sets, they unfortunately perform poorly in general. In this work we present the novel algorithm DimDraw to draw order diagrams. This algorithm is based on a relation between the dimension of an ordered set and the bipartiteness of a corresponding graph.

cs.CG↗

arXiv2019

Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields

The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research objectives have been stated, there is still the need to clarify some terms such as information, knowledge, and experience in the context of CIL and to differentiate CIL from recent and ongoing research in related fields such as active learning, collaborative learning, and others. Both aspects are addressed in this paper.

cs.LG↗

arXiv2019

DimDraw -- A novel tool for drawing concept lattices

Concept lattice drawings are an important tool to visualize complex relations in data in a simple manner to human readers. Many attempts were made to transfer classical graph drawing approaches to order diagrams. Although those methods are satisfying for some lattices they unfortunately perform poorly in general. In this work we present a novel tool to draw concept lattices that is purely motivated by the order structure.

cs.CG↗

arXiv2019

Discovering Implicational Knowledge in Wikidata

Knowledge graphs have recently become the state-of-the-art tool for representing the diverse and complex knowledge of the world. Examples include the proprietary knowledge graphs of companies such as Google, Facebook, IBM, or Microsoft, but also freely available ones such as YAGO, DBpedia, and Wikidata. A distinguishing feature of Wikidata is that the knowledge is collaboratively edited and curated. While this greatly enhances the scope of Wikidata, it also makes it impossible for a single individual to grasp complex connections between properties or understand the global impact of edits in the graph. We apply Formal Concept Analysis to efficiently identify comprehensible implications that are implicitly present in the data. Although the complex structure of data modelling in Wikidata is not amenable to a direct approach, we overcome this limitation by extracting contextual representations of parts of Wikidata in a systematic fashion. We demonstrate the practical feasibility of our approach through several experiments and show that the results may lead to the discovery of interesting implicational knowledge. Besides providing a method for obtaining large real-world data sets for FCA, we sketch potential applications in offering semantic assistance for editing and curating Wikidata.

cs.AI↗

arXiv2018

Relevant Attributes in Formal Contexts

Computing conceptual structures, like formal concept lattices, is in the age of massive data sets a challenging task. There are various approaches to deal with this, e.g., random sampling, parallelization, or attribute extraction. A so far not investigated method in the realm of formal concept analysis is attribute selection, as done in machine learning. Building up on this we introduce a method for attribute selection in formal contexts. To this end, we propose the notion of relevant attributes which enables us to define a relative relevance function, reflecting both the order structure of the concept lattice as well as distribution of objects on it. Finally, we overcome computational challenges for computing the relative relevance through an approximation approach based on information entropy.

cs.AI↗

arXiv2018

Distances for WiFi Based Topological Indoor Mapping

For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover's Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario.

cs.LG↗

arXiv2018

Clones in Graphs

Finding structural similarities in graph data, like social networks, is a far-ranging task in data mining and knowledge discovery. A (conceptually) simple reduction would be to compute the automorphism group of a graph. However, this approach is ineffective in data mining since real world data does not exhibit enough structural regularity. Here we step in with a novel approach based on mappings that preserve the maximal cliques. For this we exploit the well known correspondence between bipartite graphs and the data structure formal context $(G,M,I)$ from Formal Concept Analysis. From there we utilize the notion of clone items. The investigation of these is still an open problem to which we add new insights with this work. Furthermore, we produce a substantial experimental investigation of real world data. We conclude with demonstrating the generalization of clone items to permutations.

cs.SI↗