{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/22487fcaa0b7c14497e1938166c668ed8/analyticcomp", "tags" : [ ], "intraHash" : "2487fcaa0b7c14497e1938166c668ed8", "interHash" : "2172caec88853ab3e42eef22856586ab", "label" : "Multiset Semantics in SPARQL, Relational Algebra and Datalog", "user" : "analyticcomp", "description" : "", "date" : "2026-03-08 16:07:42", "changeDate" : "2026-03-08 17:46:56", "count" : 3, "pub-type": "article", "journal": "Semantic Web -- Interoperability, Usability, Applicability","publisher":"SAGE", "year": "2026", "url": "", "author": [ "Renzo Angles","Claudio Gutierrez","Daniel Hernandez" ], "authors": [ {"first" : "Renzo", "last" : "Angles"}, {"first" : "Claudio", "last" : "Gutierrez"}, {"first" : "Daniel", "last" : "Hernandez"} ], "editor": [ "Cogan Shimizu","Eva Blomqvist" ], "editors": [ {"first" : "Cogan", "last" : "Shimizu"}, {"first" : "Eva", "last" : "Blomqvist"} ], "abstract": "The paper analyzes and characterizes the algebraic and logical structure of the multiset semantics for SPARQL patterns involving AND, UNION, FILTER, EXCEPT, and SELECT. To do this, we align SPARQL with two well-established query languages: Datalog and Relational Algebra. Specifically, we study (i) a version of non-recursive Datalog with safe negation extended to support multisets, and (ii) a multiset relational algebra comprising projection, selection, natural join, arithmetic union, and except. We prove that these three formalisms are expressively equivalent under multiset semantics.", "preprinturl" : "https://www.semantic-web-journal.net/content/multiset-semantics-sparql-relational-algebra-and-datalog-1", "language" : "English", "bibtexKey": "angles2025multiset" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2edaa7970da48f765505965498bcc5356/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "edaa7970da48f765505965498bcc5356", "interHash" : "f75c9153848dab2e390845d189372761", "label" : "Enhancing online lecture engagement through gaze and emotion feedback integration", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:29:23", "changeDate" : "2026-02-13 16:29:23", "count" : 2, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2025", "url": "https://elib.uni-stuttgart.de/handle/11682/16320", "author": [ "Frederik Horn" ], "authors": [ {"first" : "Frederik", "last" : "Horn"} ], "abstract": "The shift towards online meetings, seminars, and lectures has rapidly gained momentum in recent years, particularly accelerated by the events surrounding the COVID-19 pandemic. However, the absence of nonverbal cues such as eye contact and gestures in virtual settings presents significant challenges for effective communication. Existing frameworks for virtual meetings often fail to adequately address this issue, making it difficult for presenters to accurately assess audience engagement and comprehension. This thesis investigates these challenges by capturing participant attention and emotion in real-time and evaluating how presenters interact with live feedback. Through the implementation and study of a feedback system that visualizes gaze and emotional data, we aimed to bridge the gap between in-person and online lecture experiences. To ensure an informed approach, we conducted a requirement analysis prior to our experiment, identifying key factors for effective feedback integration. In the experiment, we collected data through our tool by logging meeting interactions and analyzing responses from a post-experiment questionnaire. Our findings provide insights into the impact of such feedback on presenter motivation, delivery adjustments, and engagement levels, ultimately contributing to the improvement of educational quality in virtual environments.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-16301", "bibtexKey": "https://doi.org/10.18419/opus-16301" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/299eb1047672d01136e45bf8b837fbefa/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "99eb1047672d01136e45bf8b837fbefa", "interHash" : "af04130a1ca6708d9a868b7a10168d17", "label" : "Entwicklung eines neuronalen Netzwerks zur Optimierung der Datenübertragungsqualität von Kleinsatellitenplattformen", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:27:48", "changeDate" : "2026-02-13 16:27:48", "count" : 5, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2021", "url": "http://elib.uni-stuttgart.de/handle/11682/11921", "author": [ "Cedric Holeczek" ], "authors": [ {"first" : "Cedric", "last" : "Holeczek"} ], "abstract": "Today, small satellites are an increasingly important way for researchers to launch experiments and payloads into Earth orbit. On the one hand, these satellite systems have a growing need for data transmission to a ground station; on the other hand, various constraints apply to the design and operation of radio communication systems in space. Today's radio systems usually have static transceiver configurations and the transmission rates used correspond to the worst-case consideration for the particular case. Recently, adaptive approaches for the operation of radio links between satellite and ground station have been described, in which the transceiver configuration, controlled by a learning algorithm, is changed during operation and adapted to the respective external influences. The basis for the algorithms used is the reinforcement learning model. The goal of this work was the further development of an algorithm developed for satellite communication and the testing of this algorithm within a simulation environment in order to evaluate the effects of the changes. The modified algorithm was run in a software simulation environment that included the digital signal processing of the transmitter and receiver and a model for the changing transmission conditions during a satellite overflight. The modification was compared with the original algorithm with respect to the achievable data transmission. Among other things, the number of neural networks used for learning was varied. Furthermore, different hyperparameters were varied and the effects on the data transmission were examined. An adjustment of the hyperparameters led to the transmission of 57.8% more data than in the baseline implementation of the algorithm. Both, the change in architecture and the reduction in the number of neural networks executed in parallel, led to slight performance losses of 4.0% and 3.3%, respectively. The results of the software simulations performed here, however, cannot be directly transferred to hardware simulation environments or actual communication links. The implementation of the different algorithm variants allows to test these variants with hardware transmission links in the future and to test such a system on a small satellite later on.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "de", "doi" : "10.18419/OPUS-11904", "bibtexKey": "https://doi.org/10.18419/opus-11904" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2d4e36fefa58e32a5d75df11e8540b88c/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "d4e36fefa58e32a5d75df11e8540b88c", "interHash" : "4d94587b6214344ae1a614c460a27def", "label" : "Ensemble approaches for link prediction", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:25:18", "changeDate" : "2026-02-13 16:25:18", "count" : 2, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2024", "url": "http://elib.uni-stuttgart.de/handle/11682/15402", "author": [ "Tim Braun" ], "authors": [ {"first" : "Tim", "last" : "Braun"} ], "abstract": "Knowledge Graphs (KGs) are fundamental for organizing and representing large amounts of information, but they often suffer from incompleteness. Link prediction using Knowledge Graph Embedding (KGE) methods has emerged as a solution to this problem. Many different methods have been proposed to perform link prediction, some of which are a combination of different methods. However, existing approaches that combine different methods typically train models on the entire graph, lacking the diversity seen in machine learning ensembles such as bagging and random forests. In this thesis, we present the novel ensemble approaches UnifEnt and UnifFeat, that divide the KG into sub-graphs by taking advantage of the core principles of bagging and random forests. We evaluated our approach on common KG datasets and showed the benefits of using our method by comparing it to common KGE baseline methods, as well as related work in the area of ensemble methods for link prediction.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-15383", "bibtexKey": "https://doi.org/10.18419/opus-15383" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2431d43ce0d77e9cb5a72018deffbe2a9/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "431d43ce0d77e9cb5a72018deffbe2a9", "interHash" : "06be5c788ba2aea11f4a9d885918175b", "label" : "Generating random knowledge graphs from rules", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:23:45", "changeDate" : "2026-02-13 16:23:45", "count" : 7, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2024", "url": "https://elib.uni-stuttgart.de/handle/11682/15486", "author": [ "Gabriel Timon Glaser" ], "authors": [ {"first" : "Gabriel Timon", "last" : "Glaser"} ], "abstract": "A knowledge graph is a datastructure that is capable of storing knowledge. Besides that, there are several methods that use knowledge graphs to derive more information. These methods need to be validated with example knowledge graphs. However, real data might not be available or not contain desired properties. Thus, there are use cases that benefit from the generation of synthetic knowledge graphs. To define a synthetic knowledge graph, there is the need of a characterization that expresses how the synthetic data should look. In this thesis, I use Horn clauses for this characterization because of their good balance of expressiveness and complexity, their use in the field of rule mining, and their base role in the logical language Datalog. As clauses are usually not represented perfectly in real data, the goal of this thesis is to generate a knowledge graph that does not perfectly fulfil given Horn clauses, but in a desired degree of fulfillment. During the thesis, I developed and implemented two modifiable algorithms to generate knowledge graphs. On the one hand, I adapted the general hill climbing technique to generate knowledge graphs. On the other hand, I implemented a greedy algorithm which orders a given set of Horn clauses using logical subsumptions between their bodies, and then add edges to fulfil one Horn clause after the other, in the computed order. Both algorithms aim to fulfil the goal of this thesis by generating synthetic knowledge graphs according to given Horn clauses, each with a degree of fulfilment. The degree of fulfilment of any Horn clauses is characterized by body support, the number of times the premise of the Horn clauses is fulfilled, and support, the number of times the premise and conclusion of the Horn clauses are fulfilled. Additionally, there is the confidence which is the fraction of support and body support, i.e., the percentage of cases the Horn clause is fulfilled. All code is published such that anyone can try it. During the evaluation, random sets of Horn clauses were produced and the implementations generated corresponding knowledge graphs. Generated knowledge graphs were compared by considering the difference between the expected and the actual degree of fulfilment for each Horn clause. The result is that generation variant hill climbing with the initial state set to the result of the greedy algorithm with rule order based on subsumption yields the best results. Also, the difficulty of generating a good knowledge graph increases along with the overlapping degree of the input set of Horn clauses. Note that the overlapping degree reflects how many relation names occur in how many Horn clauses of the set. Lastly, the state-of-the-art mining tool AMIE found many Horn clauses in the generated graphs which were not intended by the set given to the generator.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-15467", "bibtexKey": "https://doi.org/10.18419/opus-15467" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2b8f36aff1d2561fc04476ee51c618157/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "b8f36aff1d2561fc04476ee51c618157", "interHash" : "aaec8b8fdd8806abd601625f6c1b8db6", "label" : "Bayesian symbolic regression in structured latent spaces", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:21:09", "changeDate" : "2026-02-13 16:21:09", "count" : 2, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2025", "url": "https://elib.uni-stuttgart.de/handle/11682/16319", "author": [ "Chenlei Pei" ], "authors": [ {"first" : "Chenlei", "last" : "Pei"} ], "abstract": "Symbolic regression is an interpretable machine learning method that learns mathematical expressions from given data. It naturally combines with Bayesian Inference which lets experts express their knowledge as prior distributions over equations. However, the infinite search space of mathematical expressions renders exhaustive search impractical, and Bayesian Inference remains costly. Therefore, we propose to execute the Bayesian Reasoning in the learned latent space of a trained Variational Autoencoder (VAE) and thereby exploit inherent structures in the search space. While latent spaces have been used to structure search spaces, our approach provides the probability of each mathematical expression rather than selecting the best one. We suggest practical approximations to the posterior distribution in latent space and obtain formula examples by sampling from the posterior using the Gaussian Process Hamiltonian Monte Carlo (GP-HMC) method. We have validated our method using various Koza, Nguyen, and self-generated datasets and compared it against genetic programming and SInDy concerning the Root Mean Square Error (RMSE). Keywords: Symbolic Regression, latent space, Variational Autoencoder, Character Variational Autoencoder, Grammar Variational Autoencoder, Bayesian Reasoning, Gaussian Process, Hamiltonian Monte Carlo, Gaussian Process Hamiltonian Monte Carlo.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-16300", "bibtexKey": "https://doi.org/10.18419/opus-16300" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/27b82e6e1710df1bcbdfffa0d392c620a/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "7b82e6e1710df1bcbdfffa0d392c620a", "interHash" : "5d6e9df302a82ecae042bf73c29875ab", "label" : "Low resource named entity recognition applied to oncology", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:19:32", "changeDate" : "2026-02-13 16:19:32", "count" : 2, "pub-type": "misc", "publisher":"Universität Stuttgart", "year": "2025", "url": "https://elib.uni-stuttgart.de/handle/11682/17734", "author": [ "Jonas Mahr" ], "authors": [ {"first" : "Jonas", "last" : "Mahr"} ], "abstract": "Named entity recognition (NER) is a fundamental task in Natural Language Processing (NLP) that involves identifying and classifying entities in text. NER forms the basis for solving many NLP tasks that play an important role in the biomedical domain. However, the scarcity of annotated data poses significant challenges in training effective NER models, particularly in low-resource languages, such as German. This study aims to evaluate five models in a low-resource environment, such as oncology in German, to gain insights into possible solutions to overcome this data scarcity. These approaches include prompt engineering of a Large Language Model, a BERT-based model, fine-tuned separately on the WikiMed-DE-BEL and a synthetic dataset, and a GLiNER-based model architecture. A model fine-tuned on a German gold standard oncology dataset serves as a benchmark to compare the other four models to. The evaluation is conducted using two datasets: MAED-KS, a de-identified oncology dataset consisting of patient reports collected from a German hospital, and the aluminium standard dataset, a synthetic dataset constructed based on disease co-occurrence, extracted from hospital data. Our results show that the GLiNER architecture achieves the highest F1-scores of the four approaches on the MAED-KS dataset and similar scores to the benchmark model. The Prompt Engineered Large Language Model performed best on the aluminum standard dataset. Overall, the GLiNER model shows the best performance and good adaptability in a low resource environment, such as oncology data in German.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-17715", "bibtexKey": "https://doi.org/10.18419/opus-17715" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/272e1c38db3fff47cd35e4e6d7cc7c3db/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "72e1c38db3fff47cd35e4e6d7cc7c3db", "interHash" : "16b79d3350cf1b7e50c2dfc3b2384b73", "label" : "Byte Pair Encoding for Knowledge Graph Embeddings", "user" : "analyticcomp", "description" : "", "date" : "2026-02-13 16:16:22", "changeDate" : "2026-02-13 16:17:47", "count" : 2, "pub-type": "mastersthesis", "booktitle": "Byte Pair Encoding for Knowledge Graph Embeddings","publisher":"Universität Stuttgart", "year": "2025", "url": "https://elib.uni-stuttgart.de/handle/11682/17227", "author": [ "Fatos Ferati" ], "authors": [ {"first" : "Fatos", "last" : "Ferati"} ], "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-17208", "bibtexKey": "https://doi.org/10.18419/opus-17208" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2b7aaed3d3d7fa1735900523c98a619b0/analyticcomp", "tags" : [ "ac-krbuilding" ], "intraHash" : "b7aaed3d3d7fa1735900523c98a619b0", "interHash" : "7989e5e4f3bc7d8f01103ad214624098", "label" : "geof3D: SPARQL geometric functions for co-designing buildings", "user" : "analyticcomp", "description" : "", "date" : "2025-12-25 11:41:36", "changeDate" : "2025-12-25 11:56:58", "count" : 6, "pub-type": "article", "journal": "Advanced Engineering Informatics", "year": "2026", "url": "https://www.sciencedirect.com/science/article/pii/S1474034625011541", "author": [ "Diellza Elshani","Daniel Hernandez","Ali Nakhaee","Anthony A. Arrascue","Steffen Staab","Thomas Wortmann" ], "authors": [ {"first" : "Diellza", "last" : "Elshani"}, {"first" : "Daniel", "last" : "Hernandez"}, {"first" : "Ali", "last" : "Nakhaee"}, {"first" : "Anthony A.", "last" : "Arrascue"}, {"first" : "Steffen", "last" : "Staab"}, {"first" : "Thomas", "last" : "Wortmann"} ], "volume": "71","pages": "104261","abstract": "Semantic Web technologies are increasingly used in the architecture, engineering, and construction (AEC) industry, yet the Resource Description Framework (RDF) and its query language, SPARQL, still lack native support for 3D geometry. Existing approaches either reduce geometry to 2D, rely on external spatial databases, or require processing workflows outside the semantic layer. This paper introduces geof3D, an extension to SPARQL that enables 3D geometric computation directly inside RDF triple stores. The framework is grounded in a formal function space derived from Architectural Geometry and provides typed operators for measurement, spatial predicates, constructive solid modeling, and affine transformations. These functions are implemented as SPARQL built-ins in RDF4J, supported by an execution backend that uses Java-based processing together with SFCGAL, a robust computational geometry engine accessed through the Java Native Interface (JNI). The system supports operations including geometric validation, Boolean solids, 3D spatial queries, and shape transformations without leaving the RDF environment. We evaluate geof3D using real building models from the Large-Scale Construction Robotics Laboratory and show that the framework supports spatial alignment, clash detection, and algorithmic modeling entirely through RDF-native queries. The evaluation examines both expressiveness and implementation performance, combining in-browser benchmarking with direct JNI measurements and comparative testing against a PostGIS configuration to assess performance, scalability, and geometric fidelity. All code, queries, datasets, and benchmarks are openly released. This work shows that SPARQL can serve not only as a semantic query language but also as a computational interface for 3D co-design, enabling integrated, interoperable, and geometry-aware workflows for building information management.", "issn" : "1474-0346", "doi" : "https://doi.org/10.1016/j.aei.2025.104261", "bibtexKey": "ELSHANI2026104261" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2b480034234bcca9040973629055554d0/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "b480034234bcca9040973629055554d0", "interHash" : "cce5dc7d34018c38796c60890a5fd283", "label" : "eSPARQL : design and implementation of a query language for epistemic queries on knowledge graphs", "user" : "analyticcomp", "description" : "", "date" : "2025-10-19 11:31:04", "changeDate" : "2025-10-20 08:20:11", "count" : 4, "pub-type": "article", "journal": "Department of Analytical Computing","publisher":"Universität Stuttgart", "year": "2024", "url": "https://elib.uni-stuttgart.de/handle/11682/15493", "author": [ "Xinyi Pan" ], "authors": [ {"first" : "Xinyi", "last" : "Pan"} ], "abstract": "In recent years, large-scale knowledge graphs have emerged, integrating data from various sources. Often, this data includes assertions about other assertions, establishing contexts in which these assertions hold. A recent enhancement to RDF, known as RDF-star, allows for statements about statements and is currently under consideration as a W3C standard. However, RDF-star lacks a defined semantics for such statements and lacks intrinsic mechanisms to operate on them. This thesis describes and implements a novel query language, termed eSPARQL, tailored for epistemic RDF-star metadata and grounded in four-valued logic. Our language builds on SPARQL-star, the query language for RDF-star, by incorporating an expanded FROM clause, called FROM BELIEF, designed to manage multiple, and occasionally conflicting, beliefs. eSPARQL\u2019s capabilities are demonstrated through four example queries, showcasing its ability to (i) retrieve individual beliefs, (ii) aggregate beliefs, (iii) identify conflicts between individuals, and (iv) handle nested beliefs (beliefs about beliefs). The implementation of eSPARQL developed in this thesis is built on top of an existing SPARQL-star query engine. In this implementation, the execution process of a eSPARQL consists of two phases. First, the expression in the FROM BELIEF clause, called belief query, is translated into a SPARQL-star CONSTRUCT query that generates an intermediary graph, containing the beliefs of the subjects described in the belief query. In the second phase, This intermediary graph is then processed with the graph pattern of the eSPARQL by translating it to a graph pattern that can be processed by a standard SPARQ-star engine. In this last phase, the implementation translates eSPARQL operations to SPARQL-star, and checks if the pattern contains nested eSPARQL queries to be processed recursively. We study two research questions: (RQ1) Does the eSPARQL implementation scale? and (RQ2) How the eSPARQL implementation execution times compare with the execution time of manually written SPARQL-star queries? To answer these research questions, use the four example eSPARQL queries that showcase the abilities of eSPARQL and create a synthetic dataset generator that generates graphs of multiple sizes. Additionally, for research question RQ2, we manually generate SPARQL-star queries that are equivalent to the example eSPARQL queries. Regarding research question RQ1, our results show that eSPARQL has an execution time that is proportional with the data size. Regarding research question RQ2, except for one question, the manually written SPARQL-star queries are clearly faster than our implementation. Although the implementation showed to be slower than the manually generated SPARQL-star queries, the eSPARQL queries are shorter and easier to understand. This positive aspect of eSPARQL, can motivate further studies on how to optimize the eSPARQL implementation.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-15474", "bibtexKey": "https://doi.org/10.18419/opus-15474" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2026b71528b4423a0aa6e58c4b265c3f5/analyticcomp", "tags" : [ "thesis" ], "intraHash" : "026b71528b4423a0aa6e58c4b265c3f5", "interHash" : "06be5c788ba2aea11f4a9d885918175b", "label" : "Generating random knowledge graphs from rules", "user" : "analyticcomp", "description" : "", "date" : "2025-10-18 02:23:01", "changeDate" : "2025-10-18 02:23:39", "count" : 7, "pub-type": "article", "journal": "Department of Analytic Computing","publisher":"Universität Stuttgart", "year": "2024", "url": "https://elib.uni-stuttgart.de/handle/11682/15486", "author": [ "Gabriel Timon Glaser" ], "authors": [ {"first" : "Gabriel Timon", "last" : "Glaser"} ], "abstract": "A knowledge graph is a datastructure that is capable of storing knowledge. Besides that, there are\r\nseveral methods that use knowledge graphs to derive more information. These methods need to be\r\nvalidated with example knowledge graphs. However, real data might not be available or not contain\r\ndesired properties. Thus, there are use cases that benefit from the generation of synthetic knowledge\r\ngraphs. To define a synthetic knowledge graph, there is the need of a characterization that expresses\r\nhow the synthetic data should look. In this thesis, I use Horn clauses for this characterization\r\nbecause of their good balance of expressiveness and complexity, their use in the field of rule mining,\r\nand their base role in the logical language Datalog. As clauses are usually not represented perfectly\r\nin real data, the goal of this thesis is to generate a knowledge graph that does not perfectly fulfil\r\ngiven Horn clauses, but in a desired degree of fulfillment.\r\nDuring the thesis, I developed and implemented two modifiable algorithms to generate knowledge\r\ngraphs. On the one hand, I adapted the general hill climbing technique to generate knowledge\r\ngraphs. On the other hand, I implemented a greedy algorithm which orders a given set of Horn\r\nclauses using logical subsumptions between their bodies, and then add edges to fulfil one Horn\r\nclause after the other, in the computed order. Both algorithms aim to fulfil the goal of this thesis\r\nby generating synthetic knowledge graphs according to given Horn clauses, each with a degree\r\nof fulfilment. The degree of fulfilment of any Horn clauses is characterized by body support, the\r\nnumber of times the premise of the Horn clauses is fulfilled, and support, the number of times\r\nthe premise and conclusion of the Horn clauses are fulfilled. Additionally, there is the confidence\r\nwhich is the fraction of support and body support, i.e., the percentage of cases the Horn clause is\r\nfulfilled. All code is published such that anyone can try it.\r\nDuring the evaluation, random sets of Horn clauses were produced and the implementations\r\ngenerated corresponding knowledge graphs. Generated knowledge graphs were compared by\r\nconsidering the difference between the expected and the actual degree of fulfilment for each Horn\r\nclause. The result is that generation variant hill climbing with the initial state set to the result of the\r\ngreedy algorithm with rule order based on subsumption yields the best results. Also, the difficulty\r\nof generating a good knowledge graph increases along with the overlapping degree of the input\r\nset of Horn clauses. Note that the overlapping degree reflects how many relation names occur in\r\nhow many Horn clauses of the set. Lastly, the state-of-the-art mining tool AMIE found many Horn\r\nclauses in the generated graphs which were not intended by the set given to the generator.", "copyright" : "info:eu-repo/semantics/openAccess", "language" : "en", "doi" : "10.18419/OPUS-15467", "bibtexKey": "https://doi.org/10.18419/opus-15467" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24d9ff057defad16d863e8b2a453b786f/analyticcomp", "tags" : [ ], "intraHash" : "4d9ff057defad16d863e8b2a453b786f", "interHash" : "1e7f4fc0e40397388e517cea9803f7e9", "label" : "ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation", "user" : "analyticcomp", "description" : "", "date" : "2025-09-09 11:36:52", "changeDate" : "2025-09-09 11:36:52", "count" : 3, "pub-type": "inproceedings", "booktitle": "Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning", "year": "2025", "url": "https://arxiv.org/abs/2508.20131", "author": [ "Yuqicheng Zhu","Nico Potyka","Daniel Hernández","Yuan He","Zifeng Ding","Bo Xiong","Dongzhuoran Zhou","Evgeny Kharlamov","Steffen Staab" ], "authors": [ {"first" : "Yuqicheng", "last" : "Zhu"}, {"first" : "Nico", "last" : "Potyka"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Yuan", "last" : "He"}, {"first" : "Zifeng", "last" : "Ding"}, {"first" : "Bo", "last" : "Xiong"}, {"first" : "Dongzhuoran", "last" : "Zhou"}, {"first" : "Evgeny", "last" : "Kharlamov"}, {"first" : "Steffen", "last" : "Staab"} ], "volume": "284","pages": "1-22","abstract": "Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.", "venue" : "Santa Cruz, California", "language" : "en", "eventdate" : "Sep 10", "preprinturl" : "https://arxiv.org/abs/2508.20131", "bibtexKey": "zhu2025argrag" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2ae004ef7ce367b17625832057af85483/analyticcomp", "tags" : [ "myown" ], "intraHash" : "ae004ef7ce367b17625832057af85483", "interHash" : "61eed638f52ae72f2ff58dc761945acb", "label" : "ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation", "user" : "analyticcomp", "description" : "", "date" : "2025-09-08 16:03:01", "changeDate" : "2025-09-08 19:02:17", "count" : 1, "pub-type": "inproceedings", "booktitle": "Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning", "year": "2025", "url": "https://arxiv.org/abs/2508.20131", "author": [ "Yuqicheng Zhu","Nico Potyka","Daniel Hernández","Yuan He","Zifeng Ding","Bo Xiong","Dongzhuoran Zhou","Evgeny Kharlamov","Steffen Staab" ], "authors": [ {"first" : "Yuqicheng", "last" : "Zhu"}, {"first" : "Nico", "last" : "Potyka"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Yuan", "last" : "He"}, {"first" : "Zifeng", "last" : "Ding"}, {"first" : "Bo", "last" : "Xiong"}, {"first" : "Dongzhuoran", "last" : "Zhou"}, {"first" : "Evgeny", "last" : "Kharlamov"}, {"first" : "Steffen", "last" : "Staab"} ], "volume": "284","pages": "1-22","abstract": "Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.", "venue" : "Santa Cruz, California", "language" : "en", "eventdate" : "Sep 10", "preprinturl" : "https://arxiv.org/abs/2508.20131", "bibtexKey": "zhu2025argrag" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2215032e568d60595a407e63f18e51f99/analyticcomp", "tags" : [ "ac-circularfactory" ], "intraHash" : "215032e568d60595a407e63f18e51f99", "interHash" : "464fd4545855b935a2171164ef056ba5", "label" : "A Roadmap to Create a Knowledge Graph for the Circular Factory for the Perpetual Product", "user" : "analyticcomp", "description" : "", "date" : "2025-09-07 08:18:46", "changeDate" : "2025-09-07 08:18:46", "count" : 3, "pub-type": "inproceedings", "booktitle": "Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability (KG4S 2025) co-located with the 22nd Extended Semantic Web Conference (ESWC 2025)","series": "CEUR Workshop Proceedings","publisher":"CEUR-WS.org", "year": "2025", "url": "https://ceur-ws.org/Vol-4002/short8.pdf", "author": [ "Ratan Bahadur Thapa","Daniel Hernández","Nico Brandt","Jan-Felix Klein","Etienne Hoffmann","Steffen Staab","Michael Selzer","Gisela Lanza" ], "authors": [ {"first" : "Ratan Bahadur", "last" : "Thapa"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Nico", "last" : "Brandt"}, {"first" : "Jan-Felix", "last" : "Klein"}, {"first" : "Etienne", "last" : "Hoffmann"}, {"first" : "Steffen", "last" : "Staab"}, {"first" : "Michael", "last" : "Selzer"}, {"first" : "Gisela", "last" : "Lanza"} ], "editor": [ "Eva Blomqvist","Raúl Garc\\'ıa-Castro","Daniel Hernández","Pascal Hitzler","Mikael Lindecrantz","Mar\\'ıa Poveda-Villalón" ], "editors": [ {"first" : "Eva", "last" : "Blomqvist"}, {"first" : "Raúl", "last" : "Garc\\'ıa-Castro"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Pascal", "last" : "Hitzler"}, {"first" : "Mikael", "last" : "Lindecrantz"}, {"first" : "Mar\\'ıa", "last" : "Poveda-Villalón"} ], "volume": "4002","pages": "46--52","abstract": "New economic systems are needed to decouple resource consumption from wealth. The linear economic approach of \u201Ctake-make-use-dispose\u201D is not a recipe for success in the long term. Circular production offers a solution to this problem. Our Collaborative Research Center 1574 aims to enable integrated linear and circular production on an industrial scale. To this end, the Collaborative Research Center 1574 investigates how used products and their multiple generations can achieve the vision of the perpetual product. This research involves multiple scientific questions related to production technology, product development and materials technology, ergonomics, robotics, computer science, and knowledge modeling. The Collaborative Research Center 1574 involves eighteen subprojects. Each one studies a dimension of these multiple scientific questions. One of these subprojects, called INF, aims to provide an infrastructure and teach the other subprojects\u2019 researchers how to operate and integrate all the data they produced into a unified knowledge graph. This paper describes the roadmap of the INF subproject, including the ongoing work, future steps, and vision of the INF subproject.", "venue" : "Portoroz, Slovenia", "eventdate" : "June 1st", "bibsource" : "dblp computer science bibliography, https://dblp.org", "bibtexKey": "thapa2025roadmap" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2078023f3383da5824accebc92d32f750/analyticcomp", "tags" : [ "ac","ki" ], "intraHash" : "078023f3383da5824accebc92d32f750", "interHash" : "f65c24b471755c74e31af094ba2fdc09", "label" : "Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings", "user" : "analyticcomp", "description" : "", "date" : "2025-08-19 19:42:38", "changeDate" : "2025-08-19 22:48:44", "count" : 3, "pub-type": "inproceedings", "booktitle": "Findings of the Association for Computational Linguistics, ACL 2025","publisher":"Association for Computational Linguistics", "year": "2025", "url": "https://aclanthology.org/2025.findings-acl.215/", "author": [ "Yuqicheng Zhu","Daniel Hernández","Yuan He","Zifeng Ding","Bo Xiong","Evgeny Kharlamov","Steffen Staab" ], "authors": [ {"first" : "Yuqicheng", "last" : "Zhu"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Yuan", "last" : "He"}, {"first" : "Zifeng", "last" : "Ding"}, {"first" : "Bo", "last" : "Xiong"}, {"first" : "Evgeny", "last" : "Kharlamov"}, {"first" : "Steffen", "last" : "Staab"} ], "editor": [ "Wanxiang Che","Joyce Nabende","Ekaterina Shutova","Mohammad Taher Pilehvar" ], "editors": [ {"first" : "Wanxiang", "last" : "Che"}, {"first" : "Joyce", "last" : "Nabende"}, {"first" : "Ekaterina", "last" : "Shutova"}, {"first" : "Mohammad Taher", "last" : "Pilehvar"} ], "pages": "4145--4167","abstract": "Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications. A recent work applies conformal prediction to KGE methods, providing uncertainty estimates by generating a set of answers that is guaranteed to include the true answer with a predefined confidence level. However, existing methods provide probabilistic guarantees averaged over a reference set of queries and answers (marginal coverage guarantee). In high-stakes applications such as medical diagnosis, a stronger guarantee is often required: the predicted sets must provide consistent coverage per query (conditional coverage guarantee). We propose CondKGCP, a novel method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets. CondKGCP merges predicates with similar vector representations and augments calibration with rank information. We prove the theoretical guarantees and demonstrate empirical effectiveness of CondKGCP by comprehensive evaluations.", "venue" : "Vienna, Austria", "eventdate" : "July 27 - August 1, 2025", "bibsource" : "dblp computer science bibliography, https://dblp.org", "preprinturl" : "https://arxiv.org/abs/2505.16877", "doi" : "10.18653/v1/2025.findings-acl.215", "bibtexKey": "DBLP:conf/acl/Zhu00DXKS25" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/28e4497b9b1413a5304cef79d29c75932/analyticcomp", "tags" : [ "ki" ], "intraHash" : "8e4497b9b1413a5304cef79d29c75932", "interHash" : "8c917b2aa80bb0efd8f3f7e3c7b4f433", "label" : "Is Complex Query Answering Really Complex?", "user" : "analyticcomp", "description" : "", "date" : "2025-08-16 13:30:24", "changeDate" : "2025-08-20 03:26:17", "count" : 3, "pub-type": "inproceedings", "booktitle": "Forty-Second International Conference on Machine Learning", "year": "2025", "url": "", "author": [ "Cosimo Gregucci","Bo Xiong","Daniel Hernandez","Lorenzo Loconte","Pasquale Minervini","Steffen Staab","Antonio Vergari" ], "authors": [ {"first" : "Cosimo", "last" : "Gregucci"}, {"first" : "Bo", "last" : "Xiong"}, {"first" : "Daniel", "last" : "Hernandez"}, {"first" : "Lorenzo", "last" : "Loconte"}, {"first" : "Pasquale", "last" : "Minervini"}, {"first" : "Steffen", "last" : "Staab"}, {"first" : "Antonio", "last" : "Vergari"} ], "abstract": "Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.", "venue" : "Vancouver Convention Center", "language" : "en", "eventdate" : "July 13th - July 19th", "eprint" : "2410.12537", "preprinturl" : "https://arxiv.org/abs/2410.12537", "archiveprefix" : "arXiv", "primaryclass" : "cs.LG", "bibtexKey": "gregucci2025complexqueryansweringreally" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/29e5624e9f9a18006e6007f7eda3a132f/analyticcomp", "tags" : [ ], "intraHash" : "9e5624e9f9a18006e6007f7eda3a132f", "interHash" : "d6f92578b513594ef7660447fd4cf28b", "label" : "MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning", "user" : "analyticcomp", "description" : "", "date" : "2025-08-16 07:27:00", "changeDate" : "2025-08-16 07:27:00", "count" : 3, "pub-type": "inproceedings", "booktitle": "Proceedings of the International Conference on Computer Vision, ICCV 2025", "year": "2025", "url": "https://doi.org/10.48550/arXiv.2504.06740", "author": [ "Ylli Sadikaj","Hongkuan Zhou","Lavdim Halilaj","Stefan Schmid","Steffen Staab","Claudia Plant" ], "authors": [ {"first" : "Ylli", "last" : "Sadikaj"}, {"first" : "Hongkuan", "last" : "Zhou"}, {"first" : "Lavdim", "last" : "Halilaj"}, {"first" : "Stefan", "last" : "Schmid"}, {"first" : "Steffen", "last" : "Staab"}, {"first" : "Claudia", "last" : "Plant"} ], "abstract": "Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the \"exact\" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.", "venue" : "Honolulu, Hawai'i", "language" : "en", "eventdate" : "Oct 19 \u2013 23th, 2025", "eprint" : "2504.06740", "archiveprefix" : "arXiv", "primaryclass" : "cs.CV", "doi" : "10.48550/arXiv.2504.06740", "bibtexKey": "sadikaj2025multiadsdefectawaresupervisionmultitype" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2f00b6019202f95592103b45f83bf4ed6/analyticcomp", "tags" : [ "ac","ki" ], "intraHash" : "f00b6019202f95592103b45f83bf4ed6", "interHash" : "940ba273e32b509be2c6e0f4945a7377", "label" : "Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning", "user" : "analyticcomp", "description" : "", "date" : "2025-08-16 05:30:19", "changeDate" : "2025-12-08 07:32:02", "count" : 3, "pub-type": "inproceedings", "booktitle": "Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)", "year": "2025", "url": "https://ebooks.iospress.nl/doi/10.3233/FAIA251186", "author": [ "Osama Mohammed","Jiaxin Pan","Mojtaba Nayyeri","Daniel Hernández","Steffen Staab" ], "authors": [ {"first" : "Osama", "last" : "Mohammed"}, {"first" : "Jiaxin", "last" : "Pan"}, {"first" : "Mojtaba", "last" : "Nayyeri"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Steffen", "last" : "Staab"} ], "abstract": "Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods typically use snapshot graphs to encode temporal evolution. We introduce a full-history graph that instantiates one node for every entity at every time step and separates two edge sets: (i) intra-time-step edges that capture relations within a single frame and (ii) inter-time-step edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-time-step edges, a multi-head temporal-attention module attends over an entity's inter-time-step history, and a fusion module combines the two messages after every layer. Evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6\\% (vs. 74.1\\%) and raising Elliptic++ illicit-class F1 to 88.1\\% (vs. 60.4\\%). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.", "venue" : "Bologna, Italy", "language" : "en", "eventdate" : "25-30 October", "eprint" : "2508.03251", "preprinturl" : "https://arxiv.org/abs/2508.03251", "archiveprefix" : "arXiv", "primaryclass" : "cs.AI", "doi" : "10.3233/FAIA251186", "bibtexKey": "mohammed2025fullhistorygraphsedgetypedecoupled" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/235a8fca9062059342a2830b40cf1cd30/analyticcomp", "tags" : [ "ac","ki" ], "intraHash" : "35a8fca9062059342a2830b40cf1cd30", "interHash" : "340454dce1b318843a497fe197dd9aa5", "label" : "AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code", "user" : "analyticcomp", "description" : "", "date" : "2025-08-11 10:13:55", "changeDate" : "2025-08-20 11:03:42", "count" : 4, "pub-type": "inproceedings", "booktitle": "The 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS \u201925)", "year": "2025", "url": "https://doi.org/10.1145/3663547.3746360", "author": [ "Nadeen Fathallah","Daniel Hernández","Steffen Staab" ], "authors": [ {"first" : "Nadeen", "last" : "Fathallah"}, {"first" : "Daniel", "last" : "Hernández"}, {"first" : "Steffen", "last" : "Staab"} ], "pages": "25","abstract": "The vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated expertise and additional manual efforts from Web page providers. To lower their efforts and promote inclusiveness, we aim to automatically detect and correct Web accessibility violations in HTML code. While previous work has made progress in detecting certain types of accessibility violations, the problem of automatically detecting and correcting accessibility violations remains an open challenge that we address. We introduce a novel taxonomy classifying Web accessibility violations into three key categories - Syntactic, Semantic, and Layout. This taxonomy provides a structured foundation for developing our detection and correction method and redefining evaluation metrics. We propose a novel method, AccessGuru, which combines existing accessibility testing tools and Large Language Models (LLMs) to detect violations and applies taxonomy-driven prompting strategies to correct all three categories. To evaluate these capabilities, we develop a benchmark of real-world Web accessibility violations. Our benchmark quantifies syntactic and layout compliance and judges semantic accuracy through comparative analysis with human expert corrections. Evaluation against our benchmark shows that AccessGuru achieves up to 84% average violation score decrease, significantly outperforming prior methods that achieve at most 50%.", "venue" : "Denver, CO, USA. ACM, New York, NY, USA", "language" : "en", "eventdate" : "26\u201329 October, 2025", "eprint" : "2507.19549", "archiveprefix" : "arXiv", "primaryclass" : "cs.SE", "doi" : "10.1145/3663547.3746360", "bibtexKey": "fathallah2025accessguruleveragingllmsdetect" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/202f5ea52d231af20d3f82e0d2a69d385/analyticcomp", "tags" : [ ], "intraHash" : "02f5ea52d231af20d3f82e0d2a69d385", "interHash" : "4ad23afdc9acbded471d10ef84680bd6", "label" : "Conformalized Answer Set Prediction for Knowledge Graph Embedding", "user" : "analyticcomp", "description" : "", "date" : "2025-07-06 16:29:52", "changeDate" : "2025-07-06 16:29:52", "count" : 3, "pub-type": "inproceedings", "booktitle": "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","publisher":"Association for Computational Linguistics","address":"Albuquerque, New Mexico", "year": "2025", "url": "https://aclanthology.org/2025.naacl-long.32/", "author": [ "Yuqicheng Zhu","Nico Potyka","Jiarong Pan","Bo Xiong","Yunjie He","Evgeny Kharlamov","Steffen Staab" ], "authors": [ {"first" : "Yuqicheng", "last" : "Zhu"}, {"first" : "Nico", "last" : "Potyka"}, {"first" : "Jiarong", "last" : "Pan"}, {"first" : "Bo", "last" : "Xiong"}, {"first" : "Yunjie", "last" : "He"}, {"first" : "Evgeny", "last" : "Kharlamov"}, {"first" : "Steffen", "last" : "Staab"} ], "editor": [ "Luis Chiruzzo","Alan Ritter","Lu Wang" ], "editors": [ {"first" : "Luis", "last" : "Chiruzzo"}, {"first" : "Alan", "last" : "Ritter"}, {"first" : "Lu", "last" : "Wang"} ], "pages": "731--750","abstract": "Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model\u2019s predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.", "isbn" : "979-8-89176-189-6", "doi" : "10.18653/v1/2025.naacl-long.32", "bibtexKey": "zhu2025conformalized" } ] }