Dr. Stefan Lüdtke

Post-doctoral researcher

University of Mannheim
Institute for Enterprise Systems
L 15, 1–6
L15, 1–6 – Room 416
68161 Mannheim

E-mail: stefan.luedtkeuni-mannheim.de

Credit: Katrin Glückler

Research Interests

Combination of data-driven and knowledge-based AI methods
Efficient probabilistic reasoning
Human activity recognition

Short CV

Since 2021	Postdoctoral researcher at InES, University of Mannheim
2016 – 2021	Research Assistant, Institute of Visual and Analytic Computing, University of Rostock
2014 – 2016	MSc Computer Science (Specialization Smart Computing), University of Rostock
2011 – 2014	BSc Computer Science (Robotics and Automation), University of Lübeck

Marton, S., Lüdtke, S., Bartelt, C., Tschalzev, A. and Stuckenschmidt, H. (2024). Explaining neural networks without access to training data. Machine Learning, 113, 3633-3652.
Amaefule, C. O., Lüdtke, S., Klostermann, A., Hinz, C. A., Kampa, I., Kirste, T. and Teipel, S. (2023). At crossroads in a virtual city: Effect of spatial disorientation on gait variability and psychophysiological response among healthy older adults. Gerontology, 69, 450–463.
Umlauft, J., Johnson, C. W., Roux, P., Trugman, D. T., Lecointre, A., Walpersdorf, A., Nanni, U., Gimbert, F., Rouet-Leduc, B., Hulbert, C., Lüdtke, S., Marton, S. and Johnson, P. A. (2023). Mapping glacier basal sliding applying machine learning. Journal of geophysical research : JGR. F, Earth surface, 128, 1–20.
Marton, S., Lüdtke, S. and Bartelt, C. (2022). Explanations for neural networks by neural networks. Applied Sciences, 12, 1–14.
Niemann, F., Lüdtke, S., Bartelt, C. and Ten Hompel, M. (2022). Context-aware human activity recognition in industrial processes. Sensors, 22, 1–14.
Teipel, S., Amaefule, C. O., Lüdtke, S., Görß, D., Faraza, S., Bruhn, S. and Kirste, T. (2022). Prediction of disorientation by accelerometric and gait features in young and older adults navigating in a virtually enriched environment. Frontiers in Psychology, 13, 1–14.

Betz, P., Lüdtke, S., Meilicke, C. and Stuckenschmidt, H. (2024). Rule Confidence Aggregation for Knowledge Graph Completion. In , Rules and reasoning : 8th International Joint Conferrence, RuleML+RR 2024, Rucharest, Romania, September 16–18, 2024, Proceedings (S. 1–1). Lecture Notes in Computer Science, Springer: Berlin [u.a.].
Marton, S., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). GRANDE: Gradient-Based Decision Tree Ensembles for tabular data. In , International Conference on Learning Representations (S. 1–27). , OpenReview.net: .
Marton, S., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). GradTree: Learning axis-aligned decision trees with gradient descent. In , Proceedings of the 38th AAAI Conference on Artificial Intelligence (S. 14323-14331). , AAAI Press: Washington, DC.
Tschalzev, A., Nitschke, P., Kirchdorfer, L., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). Enabling mixed effects neural networks for diverse, clustered data using Monte Carlo methods. In , Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence: Jeju, 03–09 August 2024 (S. ). , International Joint Conferences on Artificial Intelligence: Jeju, South Korea.
Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2023). Outlying aspect mining via sum-product networks. In , Advances in knowledge discovery and data mining: 27th Pacific-Asia Conference on knowledge discovery and data mining, PAKDD 2023, Osaka, Japan, May 25–28, 2023 : proceedings. Part I (S. 27–38). Lecture Notes in Computer Science, Springer: Berlin [u.a.].
Marton, S., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2023). GradTree: Learning axis-aligned decision trees with gradient descent. In , (S. 1–17). , Neural Information Processing Systems Foundation, Inc. (NeurIPS): New Orleans.
Popko, M., Bader, S., Lüdtke, S. and Kirste, T. (2023). Discovering behavioural predispositions in data to improve human activity recognition. In , iWOAR '22: Proceedings of the 7th International Workshop on Sensor-Based Activity Recognition and Artificial Intelligence : September 19–20, 2022, Rostock, Germany (S. 1–7). , Association for Computing Machinery: New York, NY, USA.
Schreckenberger, C., He, Y., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2023). Online random feature forests for learning in varying feature spaces. In , Proceedings of the 37th AAAI Conference on Artificial Intelligence. Vol. 4 (S. 4587-4595). , AAAI Press: Washington, DC.
Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2022). Exchangeability-aware sum-product networks. In , Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, 23–29 July 2022 (S. 4864-4870). , International Joint Conferences on Artificial Intelligence Organization: Wien.
Oesterle, M., Bartelt, C., Lüdtke, S. and Stuckenschmidt, H. (2022). Self-learning governance of black-box multi-agent systems. In , Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XV : International Workshop, COINE 2022, virtual event, May 9, 2022, revised selected papers (S. 73–91). Lecture Notes in Computer Science, Springer: Berlin [u.a.].
Wilken, N., Cohausz, L., Schaum, J., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2022). Leveraging planning landmarks for hybrid online goal recognition. In , International Conference on Automated Planning and Scheduling ICAPS (2022) : June 13–17, 2022, virtual (S. ). , CEUR Workshop Proceedings: Aachen.

Marton, S., Lüdtke, S., Bartelt, C. and Stuckenschmidt, H. (2024). GradTree: Learning axis-aligned decision trees with gradient descent. The 38th Annual AAAI Conference on Artificial Intelligence, Vancouver, Canada.
Betz, P., Lüdtke, S., Meilicke, C. and Stuckenschmidt, H. (2023). On the aggregation of rules for knowledge graph completion. Knowledge and Logical Reasoning in the Era of Data-driven Learning Workshop@ICML 2023, Honolulu, HI.
Felske, T., Lüdtke, S., Bader, S. and Kirste, T. (2022). Activity Recognition in Assembly Tasks by Bayesian Filtering in Multi-Hypergraphs. 2nd Workshop on Graphs and more Complex Structures for Learning and Reasoning ; colocated with AAAI 2022, online.

Other Publications

Stefan Lüdtke, Marcel Gehrke, Tanya Braun, Ralf Möller, Thomas Kirste. Lifted Marginal Filtering for Asymmetric Models by Clustering-based Merging. Proceedings of the 24th European Conference on Artificial Intelligence (ECAI) 2020. [pdf]
Stefan Lüdtke, Max Schröder, Sebastian Bader, Kristian Kersting, Thomas Kirste. Lifted Filtering via Exchangeable Decomposition. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI) 2018. [pdf]
Stefan Lüdtke, Max Schröder, Frank Krüger, Sebastian Bader, Thomas Kirste. State-Space Abstractions for Probabilistic Inference: A Systematic Review. Journal of Artificial Intelligence Research (JAIR) 2018. [pdf]
Stefan Lüdtke, Fernando Moya Rueda, Waqas Ahmed, Gernot A. Fink, Thomas Kirste. Human Activity Recognition using Attribute-Based Neural Networks and Context Information. 3rd International Workshop on Deep Learning for Human Activity Recognition 2021. [pdf]
Stefan Lüdtke. Lifted Bayesian Filtering in Multi-Entity Systems. PhD thesis. 2021. [web]
Iris Hochgraeber, Christiane Pinkert, Sumaiya Suravee, Stefan Lüdtke, Margareta Halek, Bernhard Holle. Wissenschaftsbasierte Ontologieentwicklung als Grundlage für KI-basierte Beratung von pflegenden Angehörigen. Einblicke in das Projekt eDEM-CONNECT. 20. deutscher Kongress für Versorgungsforschung 2021.
Stefan Lüdtke, Wiebke Hermann, Thomas Kirste, Heike Benes, Stefan Teipel. An Algorithm for Actigraphy-based Sleep/Wake Scoring: Comparison with Polysomnography. Clinical Neurophysiology 2020. [web]
Anne Klostermann, Chimezie Amaefule, Stefan Lüdtke, Thomas Kirste, Stefan Teipel. Physiological and Gait Pattern Effects of Induced Disorientation in a 3D Virtual Environment. Alzheimer's Association International Conference (AAIC) 2020.
Charlotte Hinz, Chimezie Amaefule, Stefan Lüdtke, Thomas Kirste, Stefan Teipel. Assessing accelerometric, gait and physiological parameters of induced spatial orientation in people with MCI or mild dementia and older healthy cohorts. Alzheimer's Association International Conference (AAIC) 2020. [web]
Stefan Lüdtke, Thomas Kirste. Lifted Bayesian Filtering in Multiset Rewriting Systems. Journal of Artificial Intelligence Research (JAIR) 2020. [web]
Chimezie Amaefule, Stefan Lüdtke, Thomas Kirste, Stefan Teipel. Effect of Spatial Disorientation in a Virtual Environment on Gait and Vital Features in Patients with Dementia: Pilot Single-Blind Randomized Control Trial. JMIR Serious Games 2020. [web]
Stefan Lüdtke, Chimezie Amaefule, Thomas Kirste, Stefan Teipel. Measuring Motion Behavior to Detect Spatial Disorientation in a VR Environment. In The 13th PErvasive Technologies Related to Assistive Environments Conference (PETRA) 2020.
Stefan Lüdtke, Kristina Yordanova, Thomas Kirste. Human Activity and Context Recognition using Lifted Marginal Filtering. Proceedings of the 15th Workshop on Context Modeling and Recognition (CoMoRea) 2019. [pdf]
Stefan Lüdtke, Alejandro Molina, Kristian Kersting, Thomas Kirste. Gaussian Lifted Marginal Filtering. KI: Advances in Artificial Intelligence 2019. [pdf]
Fernando Moya Rueda, Stefan Lüdtke, Max Schröder, Kristina Yordanova, Thomas Kirste, Gernot Fink. Combining Symbolic Reasoning and Deep Learning for Human Activity Recognition. Proceedings of the 15th Workshop on Context Modeling and Recognition (CoMoRea) 2019. [pdf]
Stefan Lüdtke, Maximilian Popko, Thomas Kirste. On the Applicability of Probabilistic Programming Languages for Causal Activity Recognition. German Journal of Artificial Intelligence (Künstliche Intelligenz) 2019. [pdf]
Kristina Yordanova, Stefan Lüdtke, Sam Whitehouse, Frank Krüger, Adeline Paiement, Majid Mirmehdi, Ian Craddock, Thomas Kirste. Analysing Cooking Behaviour in Home Settings: Towards Health Monitoring. Sensors 2019.
Sarah Weschke, Stefan Lüdtke, Martin Gube, Matthias Weippert, Chimezie Amaefule, Sven Bruhn, Rainer Bader, Thomas Kirste, Stefan Teipel. Measuring Gait Characteristics of Induced Disorientation in a VR Environment. 11. Kongress der Deutschen Gesellschaft für Biomechanik (DGfB) 2019.
Chimezie Amaefule, Stefan Lüdtke, Sarah Weschke, Christoph Berger, Sven Bruhn, Rainer Bader, Thomas Kirste, Stefan Teipel. Assessing Gait and Physiological Characteristics of Induced Disorientation in a VR Environment – The journey so far. Deutsche Gesellschaft für Psychiatrie und Psychotherapie, Psychosomatik und Nervenheilkunde (DGPPN) Kongress 2019.
Stefan Lüdtke, Max Schröder, Thomas Kirste. Approximate Probabilistic Parallel Multiset Rewriting using MCMC. KI: Advances in Artificial Intelligence 2018. [pdf]
Sam Whitehouse, Kristina Yordanova, Stefan Lüdtke, Adeline Paiement, Majid Mirmehdi. Evaluation of cupboard door sensors for improving activity recognition in the kitchen. PerCom Workshops Proceedings (PerHealth) 2018. [pdf]
Stefan Lüdtke, Max Schröder, Frank Krüger, Thomas Kirste. Where are my colleagues? Tracking and Counting Multiple Persons using Lifted Marginal Filtering. Procedings of the 4th international Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) 2017. [pdf]
Stefan Lüdtke, Albert Hein, Frank Krüger, Sebastian Bader, Thomas Kirste. Actigraphic Sleep Detection for Real-World Data of Healthy Young Adults and People with Alzheimer’s Disease. Proceedings of BIOSIGNALS 2017 (BIOSIGNALS) 2017. [pdf]
Max Schröder, Stefan Lüdtke, Sebastian Bader, Frank Krüger, Thomas Kirste. Abstracting from Observation-equivalent Entities in Human Behavior Modeling. AAAI Workshop: Plan, Activity, and Intent Recognition (PAIR) 2017. [pdf]
Max Schröder, Stefan Lüdtke, Sebastian Bader, Frank Krüger, Thomas Kirste. Sequential Lifted Bayesian Filtering in Multiset Rewriting Systems. UAI Workshop: Statistical Relational Artificial Intelligence (StarAI) 2017. [pdf]
Max Schröder, Stefan Lüdtke, Sebastian Bader, Frank Krüger, Thomas Kirste. LiMa: Sequential Lifted Marginal Filtering on Multiset State Descriptions. KI: Advances in Artificial Intelligence 2017. [pdf]