@inbook{62701, abstract = {{Learning continuous vector representations for knowledge graphs has significantly improved state-of-the-art performances in many challenging tasks. Yet, deep-learning-based models are only post-hoc and locally explainable. In contrast, learning Web Ontology Language (OWL) class expressions in Description Logics (DLs) is ante-hoc and globally explainable. However, state-of-the-art learners have two well-known lim-itations: scaling to large knowledge graphs and handling missing infor-mation. Here, we present a decision-tree-based learner (tDL) to learn Web Ontology Languages (OWLs) class expressions over large knowl-edge graphs, while imputing missing triples. Given positive and negative example individuals, tDL firstly constructs unique OWL expressions in .SHOIN from concise bounded descriptions of individuals. Each OWL class expression is used as a feature in a binary classification problem to represent input individuals. Thereafter, tDL fits a CART decision tree to learn Boolean decision rules distinguishing positive examples from nega-tive examples. A final OWL expression in.SHOIN is built by traversing the built CART decision tree from the root node to leaf nodes for each positive example. By this, tDL can learn OWL class expressions without exploration, i.e., the number of queries to a knowledge graph is bounded by the number of input individuals. Our empirical results show that tDL outperforms the current state-of-the-art models across datasets. Impor-tantly, our experiments over a large knowledge graph (DBpedia with 1.1 billion triples) show that tDL can effectively learn accurate OWL class expressions, while the state-of-the-art models fail to return any results. Finally, expressions learned by tDL can be seamlessly translated into natural language explanations using a pre-trained large language model and a DL verbalizer.}}, author = {{Demir, Caglar and Yekini, Moshood and Röder, Michael and Mahmood, Yasir and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783032060655}}, issn = {{0302-9743}}, keywords = {{Decision Tree, OWL Class Expression Learning, Description Logic, Knowledge Graph, Large Language Model, Verbalizer}}, location = {{Porto, Portugal}}, publisher = {{Springer Nature Switzerland}}, title = {{{Tree-Based OWL Class Expression Learner over Large Graphs}}}, doi = {{10.1007/978-3-032-06066-2_29}}, year = {{2025}}, } @article{35602, abstract = {{Continuous Speech Separation (CSS) has been proposed to address speech overlaps during the analysis of realistic meeting-like conversations by eliminating any overlaps before further processing. CSS separates a recording of arbitrarily many speakers into a small number of overlap-free output channels, where each output channel may contain speech of multiple speakers. This is often done by applying a conventional separation model trained with Utterance-level Permutation Invariant Training (uPIT), which exclusively maps a speaker to an output channel, in sliding window approach called stitching. Recently, we introduced an alternative training scheme called Graph-PIT that teaches the separation network to directly produce output streams in the required format without stitching. It can handle an arbitrary number of speakers as long as never more of them overlap at the same time than the separator has output channels. In this contribution, we further investigate the Graph-PIT training scheme. We show in extended experiments that models trained with Graph-PIT also work in challenging reverberant conditions. Models trained in this way are able to perform segment-less CSS, i.e., without stitching, and achieve comparable and often better separation quality than the conventional CSS with uPIT and stitching. We simplify the training schedule for Graph-PIT with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR) loss. It eliminates unfavorable properties of the previously used A-SDR loss and thus enables training with Graph-PIT from scratch. Graph-PIT training relaxes the constraints w.r.t. the allowed numbers of speakers and speaking patterns which allows using a larger variety of training data. Furthermore, we introduce novel signal-level evaluation metrics for meeting scenarios, namely the source-aggregated scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR), which are generalizations of the commonly used SDR-based metrics for the CSS case.}}, author = {{von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}}, issn = {{2329-9290}}, journal = {{IEEE/ACM Transactions on Audio, Speech, and Language Processing}}, keywords = {{Continuous Speech Separation, Source Separation, Graph-PIT, Dynamic Programming, Permutation Invariant Training}}, pages = {{576--589}}, publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}}, title = {{{Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria}}}, doi = {{10.1109/taslp.2022.3228629}}, volume = {{31}}, year = {{2023}}, } @inproceedings{44390, abstract = {{The development of autonomous vehicles and their introduction in urban traffic offer many opportunities for traffic improvements. In this paper, an approach for a future traffic control system for mixed autonomy traffic environments is presented. Furthermore, a simulation framework based on the city of Paderborn is introduced to enable the development and examination of such a system. This encompasses multiple elements including the road network itself, traffic lights, sensors as well as methods to analyse the topology of the network. Furthermore, a procedure for traffic demand generation and routing is presented based on statistical data of the city and traffic data obtained by measurements. The resulting model can receive and apply the generated control inputs and in turn generates simulated sensor data for the control system based on the current system state.}}, author = {{Link, Christopher and Malena, Kevin and Gausemeier, Sandra and Trächtler, Ansgar}}, booktitle = {{Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems}}, isbn = {{978-989-758-652-1}}, keywords = {{Traffic Simulation, Traffic Control, Car2X, Mixed Autonomy, Autonomous Vehicles, SUMO, Sensor Simulation, Traffic Demand Generation, Routing, Traffic Lights, Graph Analysis, Traffic Observer}}, location = {{Prague, Czech Republic}}, publisher = {{SCITEPRESS - Science and Technology Publications}}, title = {{{Simulation Environment for Traffic Control Systems Targeting Mixed Autonomy Traffic Scenarios}}}, doi = {{10.5220/0011987600003479}}, year = {{2023}}, } @inproceedings{33957, abstract = {{Manufacturing companies are challenged to make the increasingly complex work processes equally manageable for all employees to prevent an impending loss of competence. In this contribution, an intelligent assistance system is proposed enabling employees to help themselves in the workplace and provide them with competence-related support. This results in increasing the short- and long-term efficiency of problem solving in companies.}}, author = {{Deppe, Sahar and Brandt, Lukas and Brünninghaus, Marc and Papenkordt, Jörg and Heindorf, Stefan and Tschirner-Vinke, Gudrun}}, keywords = {{Assistance system, Knowledge graph, Information retrieval, Neural networks, AR}}, location = {{Stuttgart}}, title = {{{AI-Based Assistance System for Manufacturing}}}, doi = {{10.1109/ETFA52439.2022.9921520}}, year = {{2022}}, } @inproceedings{32509, abstract = {{ We consider fact-checking approaches that aim to predict the veracity of assertions in knowledge graphs. Five main categories of fact-checking approaches for knowledge graphs have been proposed in the recent literature, of which each is subject to partially overlapping limitations. In particular, current text-based approaches are limited by manual feature engineering. Path-based and rule-based approaches are limited by their exclusive use of knowledge graphs as background knowledge, and embedding-based approaches suffer from low accuracy scores on current fact-checking tasks. We propose a hybrid approach—dubbed HybridFC—that exploits the diversity of existing categories of fact-checking approaches within an ensemble learning setting to achieve a significantly better prediction performance. In particular, our approach outperforms the state of the art by 0.14 to 0.27 in terms of Area Under the Receiver Operating Characteristic curve on the FactBench dataset. Our code is open-source and can be found at https://github.com/dice-group/HybridFC.}}, author = {{Qudus, Umair and Röder, Michael and Saleem, Muhammad and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{The Semantic Web -- ISWC 2022}}, editor = {{Sattler, Ulrike and Hogan, Aidan and Keet, Maria and Presutti, Valentina}}, isbn = {{978-3-031-19433-7}}, keywords = {{fact checking · ensemble learning · knowledge graph veracit}}, location = {{Hanghzou, China}}, pages = {{462----480}}, publisher = {{Springer International Publishing}}, title = {{{HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs}}}, doi = {{10.1007/978-3-031-19433-7_27}}, year = {{2022}}, } @inproceedings{27381, abstract = {{Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the family of so-called RankGNNs, a combination of neural Learning to Rank (LtR) methods and GNNs. RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.}}, author = {{Damke, Clemens and Hüllermeier, Eyke}}, booktitle = {{Proceedings of The 24th International Conference on Discovery Science (DS 2021)}}, editor = {{Soares, Carlos and Torgo, Luis}}, isbn = {{9783030889418}}, issn = {{0302-9743}}, keywords = {{Graph-structured data, Graph neural networks, Preference learning, Learning to rank}}, location = {{Halifax, Canada}}, pages = {{166--180}}, publisher = {{Springer}}, title = {{{Ranking Structured Objects with Graph Neural Networks}}}, doi = {{10.1007/978-3-030-88942-5}}, volume = {{12986}}, year = {{2021}}, } @inbook{48881, abstract = {{Classic automated algorithm selection (AS) for (combinatorial) optimization problems heavily relies on so-called instance features, i.e., numerical characteristics of the problem at hand ideally extracted with computationally low-demanding routines. For the traveling salesperson problem (TSP) a plethora of features have been suggested. Most of these features are, if at all, only normalized imprecisely raising the issue of feature values being strongly affected by the instance size. Such artifacts may have detrimental effects on algorithm selection models. We propose a normalization for two feature groups which stood out in multiple AS studies on the TSP: (a) features based on a minimum spanning tree (MST) and (b) a k-nearest neighbor graph (NNG) transformation of the input instance. To this end we theoretically derive minimum and maximum values for properties of MSTs and k-NNGs of Euclidean graphs. We analyze the differences in feature space between normalized versions of these features and their unnormalized counterparts. Our empirical investigations on various TSP benchmark sets point out that the feature scaling succeeds in eliminating the effect of the instance size. Eventually, a proof-of-concept AS-study shows promising results: models trained with normalized features tend to outperform those trained with the respective vanilla features.}}, author = {{Heins, Jonathan and Bossek, Jakob and Pohl, Janina and Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal}}, booktitle = {{Proceedings of the 16th ACM/SIGEVO Conference on Foundations of Genetic Algorithms}}, isbn = {{978-1-4503-8352-3}}, keywords = {{automated algorithm selection, graph theory, instance features, normalization, traveling salesperson problem (TSP)}}, pages = {{1–15}}, publisher = {{Association for Computing Machinery}}, title = {{{On the Potential of Normalized TSP Features for Automated Algorithm Selection}}}, year = {{2021}}, } @inproceedings{19953, abstract = {{Current GNN architectures use a vertex neighborhood aggregation scheme, which limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman (WL) graph isomorphism test. Here, we propose a novel graph convolution operator that is based on the 2-dimensional WL test. We formally show that the resulting 2-WL-GNN architecture is more discriminative than existing GNN approaches. This theoretical result is complemented by experimental studies using synthetic and real data. On multiple common graph classification benchmarks, we demonstrate that the proposed model is competitive with state-of-the-art graph kernels and GNNs.}}, author = {{Damke, Clemens and Melnikov, Vitaly and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the 12th Asian Conference on Machine Learning (ACML 2020)}}, editor = {{Jialin Pan, Sinno and Sugiyama, Masashi}}, keywords = {{graph neural networks, Weisfeiler-Lehman test, cycle detection}}, location = {{Bangkok, Thailand}}, pages = {{49--64}}, publisher = {{PMLR}}, title = {{{A Novel Higher-order Weisfeiler-Lehman Graph Convolution}}}, volume = {{129}}, year = {{2020}}, } @article{10129, abstract = {{There are many hard conjectures in graph theory, like Tutte's 5-flow conjecture, and the 5-cycle double cover conjecture, which would be true in general if they would be true for cubic graphs. Since most of them are trivially true for 3-edge-colorable cubic graphs, cubic graphs which are not 3-edge-colorable, often called snarks, play a key role in this context. Here, we survey parameters measuring how far apart a non 3-edge-colorable graph is from being 3-edge-colorable. We study their interrelation and prove some new results. Besides getting new insight into the structure of snarks, we show that such measures give partial results with respect to these important conjectures. The paper closes with a list of open problems and conjectures.}}, author = {{Fiol, M. A. and Mazzuoccolo, Guiseppe and Steffen, Eckhard}}, journal = {{The Electronic Journal of Combinatorics}}, keywords = {{Cubic graph, Tait coloring, Snark, Boole coloring, Berge's conjecture, Tutte's 5-flow conjecture}}, number = {{4}}, title = {{{Measures of Edge-Uncolorability of Cubic Graphs}}}, volume = {{25}}, year = {{2018}}, } @article{61025, abstract = {{The concept of social dominance has been used in a plethora of studies to assess animal behaviour and relationships between individuals for nearly a century. Nevertheless, a standard approach does not yet exist to assess dominance in species that have a nonlinear or weakly linear hierarchical structure. We amassed 316 published data sets and show that 73.7% of the data sets and 90.3% of 103 species that we reviewed do not have a strongly linear structure. Herein, we present a novel method, ADAGIO, for assessing the structure of dominance networks. ADAGIO computes dominance hierarchies, in the form of directed acyclic graphs, to represent the dominance relations of a given group of animals. Thus far, most methods for computing dominance ranks assume implicitly that the dominance relation is a total order of the individuals in a group. ADAGIO does not assume or require this to be always true, and is hence more appropriate for analysing dominance hierarchies that are not strongly linear. We evaluated our approach against other frequently used methods, I&SI, David's score and Elo-rating, on 12 000 simulated data sets and on 279 interaction matrices from published, empirical data. The results from the simulated data show that ADAGIO achieves a significantly smaller error, and hence performs better when assigning ranks than other methods. Additionally, ADAGIO generated accurate dominance hierarchies for empirical data sets with a high index of linearity. Hence, our findings suggest that ADAGIO is currently the most reliable method to assess social dominance in gregarious animals living in groups of any size. Furthermore, since ADAGIO was designed to be generic, its applicability has the potential to extend beyond dominance data. The source code of our algorithm and all simulations used for this paper are publicly available at http://ngonga.github.io/adagio/.}}, author = {{Douglas, Pamela Heidi and Ngonga Ngomo, Axel-Cyrille and Hohmann, Gottfried}}, issn = {{0003-3472}}, journal = {{Animal Behaviour}}, keywords = {{aggression, behaviour, comparability, directed acyclic graph, hierarchy, linearity, nonlinearity, social rank, totality}}, pages = {{21--32}}, publisher = {{Elsevier BV}}, title = {{{A novel approach for dominance assessment in gregarious species: ADAGIO}}}, doi = {{10.1016/j.anbehav.2016.10.014}}, volume = {{123}}, year = {{2016}}, }