Author name cluster

Jens Lehmann

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

Advancing Safe Mechanical Ventilation Using Offline RL with Hybrid Actions and Clinically Aligned Rewards

Muhammad Hamza Yousuf
Jason Li
Sahar Vahdati
Raphael Theilen
Jakob Wittenstein
Jens Lehmann

Invasive mechanical ventilation (MV) is a life-sustaining therapy commonly used in the intensive care unit (ICU) for patients with severe and acute conditions. These patients frequently rely on MV for breathing. Given the high risk of death in such cases, optimal MV settings can reduce mortality, minimize ventilator-induced lung injury, shorten ICU stays, and ease the strain on healthcare resources. However, optimizing MV settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for optimizing MV settings, current methods struggle with the hybrid (continuous and discrete) nature of MV settings. Discretizing continuous settings leads to exponential growth in the action space, which limits the number of optimizable settings. Converting the predictions back to continuous can cause a distribution shift, compromising safety and performance. To address this challenge, in the IntelliLung project, we are developing an AI-based approach where we constrain the action space and employ factored action critics. This approach allows us to scale to six optimizable settings compared to 2-3 in previous studies. We adapt SOTA offline RL algorithms to operate directly on hybrid action spaces, avoiding the pitfalls of discretization. We also introduce a clinically grounded reward function based on ventilator-free days and physiological targets. Using multi-objective optimization for reward selection, we show that this leads to a more equitable consideration of all clinically relevant objectives. Notably, we develop a system in close collaboration with healthcare professionals that is aligned with real-world clinical objectives and designed with future deployment in mind.

PDF Details DOI

TIST Journal 2025 Journal Article

Exploring Large Language Models for Scientific Question Answering via Natural Language to SPARQL Translation

Antonello Meloni
Diego Reforgiato Recupero
Francesco Osborne
Angelo Salatino
Enrico Motta
Sahar Vahadati
Jens Lehmann

Translating scientific questions expressed in natural language into SPARQL queries that can be executed over knowledge graphs remains a significant challenge in the field of question answering. Recently, several prominent benchmarks, notably SciQA and DBLP-QuAD, have emerged to evaluate performance in this domain. In this paper, we provide a comprehensive analysis of the performance of language models on these benchmarks, assessing various optimization strategies. Our results indicate that the combined use of fine-tuning and prompting techniques, especially when incorporating strategic few-shot selection, produces excellent results on both benchmarks. These findings underscore an urgent need for more challenging benchmarks to better assess model capabilities. We identify key insights, common error patterns, and potential opportunities for transfer learning, and we discuss their implications for optimizing the performance of large language models in knowledge graph-based question answering tasks.

Details DOI

TMLR Journal 2024 Journal Article

A Self-Representation Learning Method for Unsupervised Feature Selection using Feature Space Basis

Prayag Tiwari
Farid Saberi Movahed
Saeed Karami
Farshad Saberi-Movahed
Jens Lehmann
Sahar Vahdati

Current methods of feature selection based on a self-representation framework use all the features of the original data in their representation framework. This issue carries over redundant and noisy features into the representation space, thereby diminishing the quality and effectiveness of the results. This work proposes a novel representation learning method, dubbed GRSSLFS (Graph Regularized Self-Representation and Sparse Subspace Learning), that mitigates the drawbacks of using all features. GRSSLFS employs an approach for constructing a basis for the feature space, which includes those features with the highest variance. The objective function of GRSSLFS is then developed based on a self-representation framework that combines subspace learning and matrix factorization of the basis matrix. Moreover, these basis features are incorporated into a manifold learning term to preserve the geometrical structure of the underlying data. We provide an effectiveness and performance evaluation on several widely-used benchmark datasets. The results show that GRSSLFS achieves a high level of performance compared to several classic and state-of-the-art feature selection methods.

PDF Details

IJCAI Conference 2022 Conference Paper

Climate Bot: A Machine Reading Comprehension System for Climate Change Question Answering

Md Rashad Al Hasan Rony
Ying Zuo
Liubov Kovriguina
Roman Teucher
Jens Lehmann

Climate change has a severe impact on the overall ecosystem of the whole world, including humankind. This demo paper presents Climate Bot - a machine reading comprehension system for question answering over documents about climate change. The proposed Climate Bot provides an interface for users to ask questions in natural language and get answers from reliable data sources. The purpose of the climate bot is to spread awareness about climate change and help individuals and communities to learn about the impact and challenges of climate change. Additionally, we open-sourced an annotated climate change dataset CCMRC to promote further research on the topic. This paper describes the dataset collection, annotation, system design, and evaluation.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Improving Inductive Link Prediction Using Hyper-Relational Facts (Extended Abstract)

Mehdi Ali
Max Berrendorf
Mikhail Galkin
Veronika Thost
Tengfei Ma
Volker Tresp
Jens Lehmann

For many years, link prediction on knowledge. graphs has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based KGs, whereas their richer counterparts, hyper-relational KGs (e. g. , Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. Our experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines. Our code is available at https: //github. com/mali-git/hyper_relational_ilp.

PDF Details DOI

AAAI Conference 2021 Conference Paper

5* Knowledge Graph Embeddings with Projective Transformations

Mojtaba Nayyeri
Sahar Vahdati
Can Aykul
Jens Lehmann

Performing link prediction using knowledge graph embedding models has become a popular approach for knowledge graph completion. Such models employ a transformation function that maps nodes via edges into a vector space in order to measure the likelihood of the links. While mapping the individual nodes, the structure of subgraphs is also transformed. Most of the embedding models designed in Euclidean geometry usually support a single transformation type – often translation or rotation, which is suitable for learning on graphs with small differences in neighboring subgraphs. However, multi-relational knowledge graphs often include multiple subgraph structures in a neighborhood (e. g. combinations of path and loop structures), which current embedding models do not capture well. To tackle this problem, we propose a novel KGE model (5F E) in projective geometry, which supports multiple simultaneous transformations – specifically inversion, reflection, translation, rotation, and homothety. The model has several favorable theoretical properties and subsumes the existing approaches. It outperforms them on most widely used link prediction benchmarks.

PDF Details

JMLR Journal 2021 Journal Article

PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings

Mehdi Ali
Max Berrendorf
Charles Tapley Hoyt
Laurent Vermue
Sahand Sharifzadeh
Volker Tresp
Jens Lehmann

Recently, knowledge graph embeddings (KGEs) have received significant attention, and several software libraries have been developed for training and evaluation. While each of them addresses specific needs, we report on a community effort to a re-design and re-implementation of PyKEEN, one of the early KGE libraries. PyKEEN 1.0 enables users to compose knowledge graph embedding models based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. It allows users to measure each component's influence individually on the model's performance. Besides, an automatic memory optimization has been realized in order to optimally exploit the provided hardware. Through the integration of Optuna, extensive hyper-parameter optimization (HPO) functionalities are provided. [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details

NeurIPS Conference 2021 Conference Paper

Relational Pattern Benchmarking on the Knowledge Graph Link Prediction Task

Afshin Sadeghi
Hirra Malik
Diego Collarana
Jens Lehmann

Knowledge graphs (KGs) encode facts about the world in a graph data structure where entities, represented as nodes, connect via relationships, acting as edges. KGs are widely used in Machine Learning, e. g. , to solve Natural Language Processing based tasks. Despite all the advancements in KGs, they plummet when it comes to completeness. Link Prediction based on KG embeddings targets the sparsity and incompleteness of KGs. Available datasets for Link Prediction do not consider different graph patterns, making it difficult to measure the performance of link prediction models on different KG settings. This paper presents a diverse set of pragmatic datasets to facilitate flexible and problem-tailored Link Prediction and Knowledge Graph Embeddings research. We define graph relational patterns, from being entirely inductive in one set to being transductive in the other. For each dataset, we provide uniform evaluation metrics. We analyze the models over our datasets to compare the model’s capabilities on a specific dataset type. Our analysis of datasets over state-of-the-art models provides a better insight into the suitable parameters for each situation, optimizing the KG-embedding-based systems.

PDF Details

AAAI Conference 2012 Conference Paper

Usage-Centric Benchmarking of RDF Triple Stores

Mohamed Morsey
Jens Lehmann
Sören Auer
Axel-Cyrille Ngonga Ngomo

A central component in many applications is the underlying data management layer. In Data-Web applications, the central component of this layer is the triple store. It is thus evident that finding the most adequate store for the application to develop is of crucial importance for individual projects as well as for data integration on the Data Web in general. In this paper, we propose a generic benchmark creation procedure for SPARQL, which we apply to the DBpedia knowledge base. In contrast to previous approaches, our benchmark is based on queries that were actually issued by humans and applications against existing RDF data not resembling a relational schema. In addition, our approach does not only take the query string but also the features of the queries into consideration during the benchmark generation process. Our generic procedure for benchmark creation is based on query-log mining, SPARQL feature analysis and clustering. After presenting the method underlying our benchmark generation algorithm, we use the generated benchmark to compare the popular triple store implementations Virtuoso, Sesame, Jena-TDB, and BigOWLIM. 1 2

PDF Details

JMLR Journal 2009 Journal Article

DL-Learner: Learning Concepts in Description Logics

Jens Lehmann

In this paper, we introduce DL-Learner, a framework for learning in description logics and OWL. OWL is the official W3C standard ontology language for the Semantic Web. Concepts in this language can be learned for constructing and maintaining OWL ontologies or for solving problems similar to those in Inductive Logic Programming. DL-Learner includes several learning algorithms, support for different OWL formats, reasoner interfaces, and learning problems. It is a cross-platform framework implemented in Java. The framework allows easy programmatic access and provides a command line interface, a graphical interface as well as a WSDL-based web service. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2009. ( edit, beta )

PDF Details