@inproceedings{62007, abstract = {{Ensemble methods are widely employed to improve generalization in machine learning. This has also prompted the adoption of ensemble learning for the knowledge graph embedding (KGE) models in performing link prediction. Typical approaches to this end train multiple models as part of the ensemble, and the diverse predictions are then averaged. However, this approach has some significant drawbacks. For instance, the computational overhead of training multiple models increases latency and memory overhead. In contrast, model merging approaches offer a promising alternative that does not require training multiple models. In this work, we introduce model merging, specifically weighted averaging, in KGE models. Herein, a running average of model parameters from a training epoch onward is maintained and used for predictions. To address this, we additionally propose an approach that selectively updates the running average of the ensemble model parameters only when the generalization performance improves on a validation dataset. We evaluate these two different weighted averaging approaches on link prediction tasks, comparing the state-of-the-art benchmark ensemble approach. Additionally, we evaluate the weighted averaging approach considering literal-augmented KGE models and multi-hop query answering tasks as well. The results demonstrate that the proposed weighted averaging approach consistently improves performance across diverse evaluation settings.}}, author = {{Sapkota, Rupesh and Demir, Caglar and Sharma, Arnab and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Proceedings of the Thirteenth International Conference on Knowledge Capture(K-CAP 2025)}}, keywords = {{Knowledge Graphs, Embeddings, Ensemble Learning}}, location = {{Dayton, OH, USA}}, publisher = {{ACM}}, title = {{{Parameter Averaging in Link Prediction}}}, doi = {{https://doi.org/10.1145/3731443.3771365}}, year = {{2025}}, } @inbook{63507, author = {{Pandit, Gaurav and Röder, Michael and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783031945748}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{Evaluating Approximate Nearest Neighbour Search Systems on Knowledge Graph Embeddings}}}, doi = {{10.1007/978-3-031-94575-5_4}}, year = {{2025}}, } @inproceedings{63572, author = {{Demir, Caglar and Yekini, Moshood Olawale and Röder, Michael and Mahmood, Yasir and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783032060655}}, issn = {{0302-9743}}, location = {{Porto}}, 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}}, } @inproceedings{63575, author = {{Kapoor, Sourabh and Sharma, Arnab and Röder, Michael and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783031945748}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{Robustness Evaluation of Knowledge Graph Embedding Models Under Non-targeted Attacks}}}, doi = {{10.1007/978-3-031-94575-5_15}}, year = {{2025}}, } @inproceedings{63573, author = {{Memariani, Adel and Röder, Michael and Sharma, Arnab and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783032095268}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{Link Prediction Under Non-targeted Attacks: Do Soft Labels Always Help?}}}, doi = {{10.1007/978-3-032-09527-5_6}}, year = {{2025}}, } @inproceedings{63574, author = {{Zhang, Quannian and Röder, Michael and Srivastava, Nikit and KOUAGOU, N'Dah Jean and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Proceedings of the Knowledge Capture Conference 2025}}, publisher = {{ACM}}, title = {{{Explainable Benchmarking through the Lense of Concept Learning}}}, doi = {{10.1145/3731443.3771359}}, year = {{2025}}, } @inproceedings{54449, author = {{KOUAGOU, N'Dah Jean and Demir, Caglar and Zahera, Hamada Mohamed Abdelsamee and Wilke, Adrian and Heindorf, Stefan and Li, Jiayi and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2024}}, location = {{Singapore}}, publisher = {{ACM}}, title = {{{Universal Knowledge Graph Embeddings}}}, doi = {{10.1145/3589335.3651978}}, year = {{2024}}, } @inbook{54412, author = {{Firmansyah, Asep Fajar and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{The Semantic Web}}, isbn = {{9783031606250}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{ESLM: Improving Entity Summarization by Leveraging Language Models}}}, doi = {{10.1007/978-3-031-60626-7_9}}, year = {{2024}}, } @inbook{54580, author = {{Mahmood, Yasir and Virtema, Jonni and Barlag, Timon and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783031569395}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{Computing Repairs Under Functional and Inclusion Dependencies via Argumentation}}}, doi = {{10.1007/978-3-031-56940-1_2}}, year = {{2024}}, } @article{54092, author = {{Kontinen, Juha and Mahmood, Yasir and Meier, Arne and Vollmer, Heribert}}, journal = {{Mathematical Structures in Computer Science}}, keywords = {{dice mahmood}}, pages = {{1--15}}, publisher = {{Cambridge University Press}}, title = {{{Parameterized Complexity of Weighted Team Definability}}}, doi = {{10.1017/S0960129524000033}}, year = {{2024}}, } @inproceedings{56213, author = {{Sapkota, Rupesh and Köhler, Dominik and Heindorf, Stefan}}, booktitle = {{Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM ’24),}}, location = {{Boise, Idaho, USA}}, publisher = {{ACM}}, title = {{{EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs}}}, doi = {{10.1145/3627673.3679904}}, year = {{2024}}, } @inbook{56214, author = {{Li, Jiayi and Satheesh, Sheetal and Heindorf, Stefan and Moussallem, Diego and Speck, René and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Communications in Computer and Information Science}}, isbn = {{9783031637865}}, issn = {{1865-0929}}, location = {{Malta, Valletta}}, publisher = {{Springer Nature Switzerland}}, title = {{{AutoCL: AutoML for Concept Learning}}}, doi = {{10.1007/978-3-031-63787-2_7}}, year = {{2024}}, } @article{59911, abstract = {{AbstractIn this article, we study the complexity of weighted team definability for logics with team semantics. This problem is a natural analog of one of the most studied problems in parameterized complexity, the notion of weighted Fagin-definability, which is formulated in terms of satisfaction of first-order formulas with free relation variables. We focus on the parameterized complexity of weighted team definability for a fixed formula $\varphi$ of central team-based logics. Given a first-order structure $\mathcal{A}$ and the parameter value $k\in \mathbb N$ as input, the question is to determine whether $\mathcal{A},T\models \varphi$ for some team T of size k. We show several results on the complexity of this problem for dependence, independence, and inclusion logic formulas. Moreover, we also relate the complexity of weighted team definability to the complexity classes in the well-known W-hierarchy as well as paraNP.}}, author = {{Kontinen, Juha and Mahmood, Yasir and Meier, Arne and Vollmer, Heribert}}, issn = {{0960-1295}}, journal = {{Mathematical Structures in Computer Science}}, number = {{5}}, pages = {{375--389}}, publisher = {{Cambridge University Press (CUP)}}, title = {{{Parameterized complexity of weighted team definability}}}, doi = {{10.1017/s0960129524000033}}, volume = {{34}}, year = {{2024}}, } @inbook{57323, author = {{Karalis, Nikolaos and Bigerl, Alexander and Demir, Caglar and Heidrich, Liss and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783031703645}}, issn = {{0302-9743}}, publisher = {{Springer Nature Switzerland}}, title = {{{Evaluating Negation with Multi-way Joins Accelerates Class Expression Learning}}}, doi = {{10.1007/978-3-031-70365-2_12}}, year = {{2024}}, } @inproceedings{58377, abstract = {{The connection between inconsistent databases and Dung's abstract argumentation framework has recently drawn growing interest. Specifically, an inconsistent database, involving certain types of integrity constraints such as functional and inclusion dependencies, can be viewed as an argumentation framework in Dung's setting. Nevertheless, no prior work has explored the exact expressive power of Dung's theory of argumentation when compared to inconsistent databases and integrity constraints. In this paper, we close this gap by arguing that an argumentation framework can also be viewed as an inconsistent database. We first establish a connection between subset-repairs for databases and extensions for AFs, considering conflict-free, naive, admissible, and preferred semantics. Further, we define a new family of attribute-based repairs based on the principle of maximal content preservation. The effectiveness of these repairs is then highlighted by connecting them to stable, semi-stable, and stage semantics. Our main contributions include translating an argumentation framework into a database together with integrity constraints. Moreover, this translation can be achieved in polynomial time, which is essential in transferring complexity results between the two formalisms.}}, author = {{Mahmood, Yasir and Hecher, Markus and Ngonga Ngomo, Axel-Cyrille}}, title = {{{Dung's Argumentation Framework: Unveiling the Expressive Power with Inconsistent Databases}}}, doi = {{10.1609/AAAI.V39I14.33651}}, year = {{2024}}, } @inbook{57238, abstract = {{Abstract argumentation is a popular toolkit for modeling, evaluating, and comparing arguments. Relationships between arguments are specified in argumentation frameworks (AFs), and conditions are placed on sets (extensions) of arguments that allow AFs to be evaluated. For more expressiveness, AFs are augmented with acceptance conditions on directly interacting arguments or a constraint on the admissible sets of arguments, resulting in dialectic frameworks or constrained argumentation frameworks. In this paper, we consider flexible conditions for rejecting an argument from an extension, which we call rejection conditions (RCs). On the technical level, we associate each argument with a specific logic program. We analyze the resulting complexity, including the structural parameter treewidth. Rejection AFs are highly expressive, giving rise to natural problems on higher levels of the polynomial hierarchy.}}, author = {{Fichte, Johannes K. and Hecher, Markus and Mahmood, Yasir and Meier, Arne}}, booktitle = {{Frontiers in Artificial Intelligence and Applications}}, isbn = {{9781643685489}}, issn = {{0922-6389}}, location = {{Santiago de Compostela, Spain}}, publisher = {{IOS Press}}, title = {{{Rejection in Abstract Argumentation: Harder Than Acceptance?}}}, doi = {{10.3233/faia240867}}, year = {{2024}}, } @inproceedings{55655, abstract = {{Argumentation is a well-established formalism for nonmonotonic reasoning, with popular frameworks being Dung’s abstract argumentation (AFs) or logic-based argumentation (Besnard-Hunter’s framework). Structurally, a set of formulas forms support for a claim if it is consistent, subset-minimal, and implies the claim. Then, an argument comprises support and a claim. We observe that the computational task (ARG) of asking for support of a claim in a knowledge base is “brave”, since many claims with a single support are accepted. As a result, ARG falls short when it comes to the question of confidence in a claim, or claim strength. In this paper, we propose a concept for measuring the (acceptance) strength of claims, based on counting supports for a claim. Further, we settle classical and structural complexity of counting arguments favoring a given claim in propositional knowledge bases (KBs). We introduce quantitative reasoning to measure the strength of claims in a KB and to determine the relevance strength of a formula for a claim.}}, author = {{Hecher, Markus and Mahmood, Yasir and Meier, Arne and Schmidt, Johannes}}, booktitle = {{Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence}}, publisher = {{International Joint Conferences on Artificial Intelligence Organization}}, title = {{{Quantitative Claim-Centric Reasoning in Logic-Based Argumentation}}}, doi = {{10.24963/ijcai.2024/377}}, year = {{2024}}, } @unpublished{57814, abstract = {{We study consistent query answering via different graph representations. First, we introduce solution-conflict hypergraphs in which nodes represent facts and edges represent either conflicts or query solutions. Considering a monotonic query and a set of antimonotonic constraints, we present an explicit algorithm for counting the number of repairs satisfying the query based on a tree decomposition of the solution-conflict hypergraph. The algorithm not only provides fixed-parameter tractability results for data complexity over expressive query and constraint classes, but also introduces a novel and potentially implementable approach to repair counting. Second, we consider the Gaifman graphs arising from MSO descriptions of consistent query answering. Using a generalization of Courcelle's theorem, we then present fixed-parameter tractability results for combined complexity over expressive query and constraint classes.}}, author = {{Hankala, Teemu and Hannula, Miika and Mahmood, Yasir and Meier, Arne}}, booktitle = {{arXiv:2412.08324}}, title = {{{Parameterised Complexity of Consistent Query Answering via Graph Representations}}}, year = {{2024}}, } @inbook{61210, abstract = {{Knowledge graphs (KGs) differ significantly over multiple different versions of the same data source. They also often contain blank nodes that do not have a constant identifier over all versions. Linking such blank nodes from different versions is a challenging task. Previous works propose different approaches to create signatures for all blank nodes based on named nodes in their neighborhood to match blank nodes with similar signatures. However, these works struggle to find a good mapping when the difference between the KGs’ versions grows too large. In this work, we propose Blink, an embedding-based approach for blank node linking. Blink merges two KGs’ versions and embeds the merged graph into a latent vector space based on translational embeddings and subsequently matches the closest pairs of blank nodes from different graphs. We evaluate our approach using real-world datasets against state-of-the-art approaches by computing the blank node matching for isomorphic graphs and graphs that contain triple changes (i.e., added or removed triples). The results indicate that Blink achieves perfect accuracy for isomorphic graphs. For graph versions that contain changes, such as having up to 20% of triples removed in one version, Blink still produces a mapping with an Optimal Mapping Deviation Ratio of under 1%. These results show that Blink leads to a better linking of KGs over different versions and similar graphs adhering to the linked data guidelines.}}, author = {{Becker, Alexander and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Lecture Notes in Computer Science}}, isbn = {{9783031778438}}, issn = {{0302-9743}}, location = {{Baltimore, USA}}, publisher = {{Springer Nature Switzerland}}, title = {{{Blink: Blank Node Matching Using Embeddings}}}, doi = {{10.1007/978-3-031-77844-5_12}}, year = {{2024}}, } @inproceedings{54084, author = {{Karalis, Nikolaos and Bigerl, Alexander and Heidrich, Liss and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{ESWC}}, keywords = {{bigerl dice enexa heidrich karalis ngonga sail sherif}}, title = {{{Efficient Evaluation of Conjunctive Regular Path Queries Using Multi-way Joins}}}, year = {{2024}}, }