Professor Ludwig-Maximilians-Universität
München (LMU Munich)E-mail (email): volker.tresp at lmu dot de Prospective students: We are
looking for students who are looking for master's thesis
projects and who have a strong mathematical background!
QCHALLenge
(Quantum-Classical Hybrid Optimization Algorithms for Logistics
and Production Line Management) is supported by the Federal
Ministry for Economic Affairs and Climate Action
with Partners
LMU, SAP, Siemens, BASF, BMW Group, and AQARIOS, 2023-2026.
Ko-Direktor der Arbeitsgruppe Technologische Wegbereiter und
Data Science der Plattform
Lernende Systeme (PLS) mit Förderung des Bundesministerium
für Bildung und Forschung (BMBF). 2022-
Invited presentation at Imperial College London in the series
"Imperial AI Talks", 2022.
QLindA
(Quantum Reinforcement Learning für industrielle Anwendungen) is
supported by the German Federal Ministry of Education and
Research with Partners Siemens AG, Fraunhofer IIS,
Ostbayerische Technische Hochschule Regensburg, and IQM Germany
GmbH, 2020-2024.
PI in ELISE (European Learning and Intelligent Systems
Excellence), a European Network of AI Excellence Centres, funded
under EU Horizon 2020, 2020-2023.
PyKEEN is our
new PyTorch-based library for knowledge graph embeddings (Project Page, Publication).
PyKEEN evolved out of a collaboration between the LMU, Uni Bonn
and TU Denmark. PyKEEN permits a comparative evaluation
of different embedding approaches, 2021.
PI in the Munich Center for Machine Learning (MCML) 2018-
Yesterday's
News
EU ITN MARIE CURIE ACTIONS on Machine Learning Frontiers in
Precision Medicine (MLFPM)
(2018-2022)
Coordinator of the BMBF funded project Machine
Learning with Knowledge Graphs (MLwin - Maschinelles Lernen
mit Wissensgraphen) 2018-2021
Coordinator of the BMWi funded project Klinische
Datenintelligenz (Clinical Data Intelligence); final
review meeting in Sept 2017 was a great success and made our
sponsors happy
Research
Interests
Our team has a
long tradition in machine learning for relational structured
domains. Currently our focus is on learning with (temporal)
knowledge graphs, where we also explore quantum computing
solutions. Our interest in cognitive
AI was the reason that we are increasingly exploring multimodal
data, such as texts, images, and videos. Foundation models are
becoming important for our work. Our
ultimate goal is to understand human level intelligence.
More research interests:
Machine Learning and Deep Learning
Cognitive AI
Robust and explainable AI
Foundation Models and Multimodal Models
Machine Learning with the Semantic Web, Linked Data, and
Knowledge Graphs
Machine Learning with Scene Graphs
Statistical Relational Learning
Tensor decompositions and multiway Neural Networks
Medical Decision Support Systems, Precision Medicine
Reinforcement Learning and Multi-Agent Systems
Quantum Computing
Biography
Volker Tresp is a professor atLudwig Maximilian University of Munich(LMU). He received
his Diploma degree in physics from theUniversity of Göttingenin 1984 and M.Sc.,
M.Phil. and Ph.D. degrees fromYale
Universityin
1986 and 1989, respectively. During his Ph.D., he worked in
Yale’sImage Processing and Analysis Group(IPAG). In 1990, he
joinedSiemenswhere
he has been heading various research teams in machine learning.
In 1997, he became Siemens Inventor of the Year for his
innovations in neural networks research and in 2018 became
the first Siemens Distinguished Research Scientist. He
revolutionized steel processing by pioneering a novel Bayesian
neural network approach that cleverly integrated
real-world data with simulated data from a prior solution.***
Renowned AI researcher, Geoff Hinton, aptly termed this
amalgamation of prior data as "Priors without Prejudice."
In 1994 he was a visiting scientist at theMassachusetts
Institute of Technologyin
theCenter for Biological and Computational
Learning, working with the
teams of Tomaso Poggio and Michael I. Jordan. He was co-editor
ofAdvances in Neural Information Processing
Systems 13. In 2011, he
was appointed professor in informatics at the LMU, where he
teaches a course on machine learning and where he is leading a
second research team. He is known for his work on Bayesian
machine learning, in particular theBayesian Committee Machineand his work onhierarchical learning with Gaussian
processes. TheIHRM, theSRM, SUNS, andRESCALare
milestones in representation learning for multi-relational
graphs. His team has been doing pioneering work on machine
learning with knowledge graphs, temporal knowledge graphs, and
scene graph analysis. The work on theTensor Brainreflects
his interest in mathematical models for cognition and
neuroscience. In 2020, he became a Fellow of theEuropean
Laboratory for Learning and Intelligent Systems(ELLIS). As
co-director (with Kristian Kersting and Paolo Frasconi), he
leads the ELLIS program "Semantic, Symbolic and Interpretable
Machine Learning".
***Subsequently, Siemens engineers adeptly tackled the
challenges of concept drift and covariate shift, ensuring the
model's adaptability to changing conditions and environments. As
a result, the project achieved remarkable success, propelling
the business unit to become a global leader in the process
industry. To this day, it stands as one of the most significant
achievements in machine learning for the process industry.
Students
Tong Liu, Ludwig
Maximilian University of Munich-VL
Jingpei
Wu, Ludwig
Maximilian University
of Munich-VL
Mutliple, including Diamond Foundry: Martin
Roscheisen was an intern in my team in 1991
Panoratio (Michael
Haft, Reimar Hofmann, 2003--): Deep data exploration
(the founders have left the company)
Horizon Robotics
(Kai Yu, 2015--): The world’s highest-valued
AI-chip unicorn
Xplain
Data (Michael Haft, 2015--): From correlation to causation
to artificial intelligence
Awards and Honors:
Co-author of the Honorable Mention Paper Award at AKBC 2022
(with Zifeng Ding, Jingpei Wu, Bailan He, Yunpu Ma, Zhen Han)
Co-author of the Best Paper Award, ISWC 2021 (with Mehdi
Ali, Max Berrendorf, Mikhail Galkin, Veronika Thost, Tengfei Ma,
Volker Tresp, and Jens Lehmann)
ELLIS Fellow (2020)
Co-author of the Best Paper Award, IEEE ICHI 2020 (with
Zhiliang Wu, Yinchong Yang, Yunpu Ma, Yushan Liu, Rui Zhao,
Michael Moor)
Co-author of the Student Best Paper Award, ISWC 2017 (with
Stephan Baier und Yunpu Ma)
Best Research Paper Nominee ISWC 2014 (with Denis Krompaß and
Maximilian Nickel)
Winner of the ISWC 2011 Semantic Web Challenge (with Irene
Celino, Daniele Dell'Aglio, Emanuele Della Valle, Marco
Balduini, Yi Huang, Tony Lee, Seon-Ho Kim)
Winner of the ESWC 2011 AI Mashup Challenge (with
Daniele Dell´Aglio, Irene Celino, Emanuele Della Valle, Ralph
Grothmann, Florian Steinke)
Best Paper Runner-up PKDD 2005 (with Shipeng Yu, Kai Yu,
Hans-Peter Kriegel)
PyKEEN is our
new PyTorch-based library for knowledge graph embeddings (Project Page, Publication).
PyKEEN evolved out of a collaboration between the LMU, Uni Bonn
and TU Denmark. PyKEEN permits a comparative evaluation
of different embedding approaches.
Thomas Decker, Michael Lebacher, Volker Tresp. Does Your
Model Think Like an Engineer? Explainable AI for Bearing Fault
Detection with Deep Learning. IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP),
2023.
Ahmed Frikha, Haokun Chen, Denis Krompaß, Thomas Runkler, and
Volker Tresp. Towards data-free domain generalization. In Asian
Conference on Machine Learning, PMLR, 2023.
Soeren Nolting, Zhen Han, and Volker Tresp. Modeling the
evolution of temporal knowledge graphs with uncertainty. arXiv
preprint arXiv:2301.04977, 2023.
Zifeng Ding, Jingpei Wu, Zongyue Li, Yunpu Ma, and Volker
Tresp. Improving Few-Shot Inductive Learning on Temporal
Knowledge Graphs using Confidence-Augmented Reinforcement
Learning. ECML-PKDD, 2023.
Alessandro Giovagnoli, Yunpu Ma, and Volker Tresp. QNEAT:
Natural Evolution of Variational Quantum Circuit Architecture. arXiv
preprint arXiv:2304.06981, 2023.
Yushan, Liu, Bailan He, Marcel Hildebrandt, Maximilian
Buchner, Daniela Inzko, Roger Wernert, Emanuel Weigel, Dagmar
Beyer, Martin Berbalk, and Volker Tresp. A Knowledge Graph
Perspective on Supply Chain Resilience. arXiv:2305.08506,
2023.
Tanveer Hannan, Rajat Koner, Maximilian Bernhard, Suprosanna
Shit, Bjoern Menze, Volker Tresp, Matthias Schubert, and Thomas
Seidl. GRAtt-VIS: Gated Residual Attention for Auto Rectifying
Video Instance Segmentation. arXiv:2305.17096, 2023.
Shuo Chen, Jindong Gu, Zhen Han, Yunpu Ma, Philip Torr, and
Volker Tresp. Benchmarking Robustness of Adaptation Methods on
Pre-trained Vision-Language Models. arXiv:2306.02080,
2023.
Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp. Can
Vision-Language Models be a Good Guesser? Exploring VLMs for
Times and Location Reasoning. arXiv:2307.06166,
2023.
Aneta Koleva, Martin Ringsquandl, and Volker Tresp.
Adversarial Attacks on Tables with Entity Swap. Workshops at the
49th International Conference on Very Large Data Bases VLDB,
2023.
Zifeng Ding, Zongyue Li, Ruoxia Qi, Jingpei Wu, Bailan He,
Yunpu Ma, Zhao Meng, Shuo Chen, Ruotong Liao, Zhen Han, and
Volker Tresp. ForecastTKGQuestions: A Benchmark for Temporal
Question Answering and Forecasting over Temporal Knowledge
Graphs. ISWC 2023.
Haokun Chen, Ahmed Frikha, Denis Krompass, Jindong Gu, and
Volker Tresp. FRAug: Tackling Federated Learning with Non-IID
Features via Representation Augmentation. ICCV 2023.
Zhen Han, Ruotong Liao, Jindong Gu, Yao Zhang, Zifeng Ding,
Yujia Gu, Heinz Koeppl, Hinrich Schütze, and Volker Tresp.
ECOLA: Enhancing Temporal Knowledge Embeddings with
Contextualized Language Representations. ACL 2023.
Jindong Gu, Volker Tresp, Yao Qin. Evaluating model robustness
to patch perturbations. ICML 2022 Shift Happens Workshop,
2022.
Aneta Koleva, Martin Ringsquandl, and Volker Tresp. Analysis
of the Attention in Tabular Language Models. In NeurIPS 2022
First Table Representation Workshop. 2022.
Zifeng, Ding, Bailan He, Yunpu Ma, Zhen Han, and Volker Tresp.
Learning Meta Representations of One-shot Relations for Temporal
Knowledge Graph Link Prediction. arXiv:2205.10621, 2022.
Guo, Jin, Zhen Han, Zhou Su, Jiliang Li, Volker Tresp, and
Yuyi Wang. Continuous Temporal Graph Networks for Event-Based
Graph Data. arXiv:2205.15924, 2022.
Ute Schmid, Volker Tresp, Matthias Bethge, Kristian
Kersting, and Rainer Stiefelhagen. Künstliche
Intelligenz – Die dritte Welle. In: Reussner, R. H.,
Koziolek, A. & Heinrich, R. (eds), INFORMATIK 2020
- Jahrestagung der Gesellschaft für Informatik e.V., 2021.
[PDF]
Ahmed Frikha, Denis Krompass, and Volker Tresp. Columbus:
Automated discovery of new multi-level features for domain
generalization via knowledge corruption. arXiv preprint
arXiv:2109.04320, 2021.
M Alam, M Ali, P Groth, P Hitzler, J Lehmann, H Paulheim, A
Rettinger, H Sack, A Sadeghi, and Volker Tresp. MLSMKG 2021:
Machine Learning with Symbolic Methods and Knowledge Graphs,
co-located with ECML PKDD, 2021
Zhen Han, Zifeng Ding, Yunpu Ma, Yujia Gu, and Volker Tresp.
Temporal knowledge graph forecasting with neural ode. arXiv:2101.05151,
2021.
Rajat Koner, Poulami Sinhamahapatra, and Volker Tresp. Scenes
and surroundings: Scene graph generation using relation
transformer. arXiv:2107.05448, 2021.
Yao Zhang, Yunpu Ma, Thomas Seidl, and Volker Tresp. Adaptive
Multi-Resolution Attention with Linear Complexity. arXiv:2108.04962,
2021.
Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr.
Adversarial examples on segmentation models can be easy to
transfer
Authors. arXiv:2111.11368, 2021.
Zifeng, Ding, Yunpu Ma, Bailan He, and Volker Tresp. A
simple but powerful graph encoder for temporal knowledge graph
completion. arXiv:2112.07791, 2021.
Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma,
Martin Ringsquandl, Mitchell Joblin, and Volker Tresp. Reasoning on Knowledge
Graphs with Debate Dynamics, AAAI Conference on
Artificial Intelligence (AAAI), 2020 [PDF]
Volker Tresp and Yunpu Ma. The Tensor Memory
Hypothesis. NIPS 2016 Workshop on Representation Learning
in Artificial and Biological Neural Networks (MLINI 2016), 2016.[PDF]
Daniel Sonntag, Volker Tresp, Sonja Zillner, Alexander
Cavallaro, Matthias Hammon, André Reis, Peter A Fasching, Martin
Sedlmayr, Thomas Ganslandt, Hans-Ulrich Prokosch, Klemens Budde,
Danilo Schmidt, Carl Hinrichs, Thomas Wittenberg, Philipp
Daumke, and Patricia G Oppelt. The
Clinical Data Intelligence Project. Informatik-Spektrum,
2016.[PDF]
Evrim Acar, Animashree Anandkumar, Lenore Mullin, Sebnem
Rusitschka, and Volker Tresp.
Tensor Computing for Internet of Things (Dagstuhl
Perspectives Workshop 16152). Dagstuhl Reports 6(4): 57-79
(2016)
2015
Volker Tresp, Cristóbal Esteban, Yinchong Yang, Stephan
Baier, and Denis Krompaß. Learning with Memory
Embeddings. NIPS 2015 Workshop on Nonparametric
Methods for Large Scale Representation Learning (extended TR), 2015. [PDF]
Denis Krompaß, Xueyan Jiang, Maximilian Nickel, and Volker
Tresp. Probabilistic
Latent-Factor Database Models. Proceedings of the ECML
workshop on Linked Data for Knowledge Discovery, 2014.[PDF]
Volker Tresp, Sonja Zillner, Maria J. Costa, Yi Huang,
Alexander Cavallaro, Peter A. Fasching, Andre Reis, Martin
Sedlmayr, Thomas Ganslandt, Klemens Budde, Carl Hinrichs, Danilo
Schmidt, Philipp Daumke, Daniel Sonntag, Thomas Wittenberg,
Patricia G. Oppelt, and Denis Krompass. Towards a New Science of
a Clinical Data Intelligence. NIPS 2013 Workshop on
Machine Learning for Clinical Data Analysis and Healthcare,
CoRR, arXiv:1311.4180 [cs.CY],2013.
Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, Maya
Ramanath, Volker Tresp, and Gerhard Weikum. Natural
Language Questions for the Web of Data.Empirical Methods
in Natural Language Processing and Natural Language Learning
(EMNLP-CoNLL'12), 2012. [PDF}
Achim Rettinger, Matthias Nickles, and Volker Tresp. Statistical
relational learning with formal ontologies. In Proceedings
of The European Conference on Machine Learning and Principles
and Practice of Knowledge Discovery in Databases (ECML PKDD),
2009. [PDF]
Volker Tresp, Yi Huang, Markus Bundschus, and Achim
Rettinger. Materializing
and querying learned knowledge. In Proceedings of
the First ESWC Workshop on Inductive Reasoning and Machine
Learning on the Semantic Web (IRMLeS 2009), 2009. [PDF]
Dieter Fensel, Frank van Harmelen, Bo Andersson, Paul
Brennan, Hamish Cunningham, Emanuele Della Valle, Florian
Fischer, Zhisheng Huang, Atanas Kiryakov, Tony Kyung
il Lee, Lael Schooler, Volker Tresp, Stefan Wesner, Michael
Witbrock, and Ning Zhong. Towards
larkc: A platform for web-scale reasoning. In Proceedings
of the 2th IEEE International Conference on Semantic Computing
(ICSC 2008), 2008.[PDF]
Achim Rettinger, Matthias Nickles, and Volker Tresp. A
statistical relational model for trust learning. In Proceeding
of 7th International Conference on Autonomous Agents and
Multiagent Systems (AAMAS 2008), 2008. [PDF]
Volker Tresp, Markus Bundschus, Achim Rettinger, and
Yi Huang. Towards
machine learning on the semantic web. In: Costa, Paulo C.
G.; D'Amato, Claudia; Fanizzi, Nicola; Laskey, Kathryn B.;
Laskey, Kenneth J.; Lukasiewicz, Thomas; Nickles, Matthias; and
Pool, Michael (Eds.): Uncertainty Reasoning for the Semantic Web
I Lecture Notes in AI, Springer, 2008. [PDF]
Achim Rettinger, Matthias Nickles, and Volker Tresp. Learning
initial trust among interacting agents. In Eleventh
International Workshop CIA 2007 on Cooperative Information
Agents. Springer 2007, September 2007. [PDF]
Zhao Xu, Volker Tresp, Kai Yu, and Hans-Peter Kriegel. Infinite
hidden relational models. In Proceedings of the
22nd International Conference on Uncertainty in Artificial
Intelligence (UAI 2006), 2006. [PDF]
Shipeng Yu, Kai Yu, and Volker Tresp. Collaborative
ordinal regression. In The 23nd International
Conference on Machine Learning (ICML 2006), 2006. [PDF]
Shipeng Yu, Kai Yu, Volker Tresp, Hans-Peter Kriegel, and
Mingrui Wu. Supervised
probabilistic principal component analysis. In 12th
ACM International Conference on Knowledge Discovery and Data
Mining (KDD 2006), 2006. [PDF]
2005
Zhao Xu, Volker Tresp, Kai Yu, Shipeng Yu, and Hans-Peter
Kriegel. Dirichlet
enhanced relational learning. In The 22nd
International Conference on Machine Learning (ICML 2005),
2005. [PDF]
Kai Yu, Shipeng Yu, and Volker Tresp. Blockwise supervised
inference on large graphs. In Proceedings of
Workshop on Learning with Partially Classified Training Data
at the 22nd International Conference on Machine Learning (ICML
2005), 2005. [PDF]
Kai Yu, Shipeng Yu, and Volker Tresp.
Multi-output regularized projection. In IEEE
Computer Society International Conference on Computer Vision
and Pattern Recognition (CVPR 2005), 2005.
[PDF]
Yi
Huang, Kai Yu, Matthias Schubert, Shipeng Yu, Volker Tresp, and Hans-Peter
Kriegel. Hierarchy-Regularized
Latent Semantic Indexing.IEEE
International Conference on Data Mining - ICDM, 2005. [PDF]
Volker Tresp. Committee
machines. In Yu Hen Hu and Jenq-Nen Hwang, editors, Handbook
for Neural Network Signal Processing. CRC Press, 2001.
[PDF]
Volker Tresp.
Scaling kernel-based systems to large data sets. Data
Mining and Knowledge Discovery, 5, Special issue on Statistical
Models for Data Mining, edited by Paolo Giudici, David
Heckerman, Joe Whittaker, 2001. [PDF]
Thomas Briegel and Volker Tresp. Dynamic neural regression models.
Technical report, Instituts für Statistik der
Ludwig-Maximilians-Universität München, 2000. Discussion Paper
181. [PDF]
Volker Tresp, Michael Haft, and Reimar Hofmann. Mixture
approximations to bayesian networks. In K. B. Laskey
and H. Prade, editors, Uncertainty in Artificial
Intelligence, Proceedings of the Fifteenth Conference.
Morgan Kaufmann Publishers, 1999. [PDF]
Harald Steck and Volker Tresp. Bayesian
Belief Networks for Data Mining. In: Proceedings des 2. Workshops
über Data Mining und Data Warehousing als Grundlage moderner
entscheidungsunterstützender Systeme. Eds.: Univ. Magdeburg.,
1999[PDF]
Reimar Hofmann and Volker Tresp. Nonlinear
markov networks for continuous variables. In M. I.
Jordan, M. S. Kearns, and S. A. Solla, editors, Advances
in Neural Information Processing Systems (NIPS*1997).
MIT Press, 1997. [PDF]
Volker Tresp, Ralph Neuneier, and Hans-Georg Zimmermann. Early
brain damage. In M. Mozer, M. I. Jordan, and
T. Petsche, editors, Advances in Neural Information
Processing Systems (NIPS*1996). MIT Press, 1996. [PDF]
Volker Tresp, Subutai Ahmad, and Ralph Neuneier. Training
neural networks with deficient data. In J. D. Cowan,
G. Tesauro, and J. Alspector, editors, Advances
in Neural Information Processing Systems (NIPS*1993).
Morgan Kaufmann, 1993. [PDF]
Volker Tresp, Jürgen Hollatz, and Subutai Ahmad. Network
structuring and training using rule-based knowledge. In
C. L. Giles, Hanson S. J., and Cowan J. D.,
editors, Advances in Neural Information Processing
Systems (NIPS*1992). Morgan Kaufman, 1992. [PDF]
Volker Tresp, Ira Leuthäusser, Martin Schlang, Ralph Neuneier,
Klaus Abraham-Fuchs, and Wolfgang Härer. The neural impulse
response filter. In International Conference on
Artificial Neural Networks II. North Holland,
1992. [PDF]
Jürgen Hollatz, Volker Tresp: Integrating Rule-Based Knowledge
into Neural Computing.
DAGM-Symposium, 1992.
Martin F. Schlang,Volker Tresp,Klaus Abraham-Fuchs,Wolfgang Härer, and P. Weismüller. Neuronale Netze zur Segmentierung und Clusterung
von biomagnetischen Signalen.DAGM-Symposium,
1992.
"Bad talks make you want to die
and good talks mess up your brain" (why one should avoid
talks) more
Origin of the name Tresp (my
best guess). Tresp is related to the Saxon (mittelniederdeutsch)
word "dreist", which means audacious. The name would really
stand for someone who comes from the village where one can
cross over the bubbling ("dreisten") brook. The brook is called
Dreisbach, the village Drespe (earlier form: Dreispe). The term is
related to the Celtic term for “bubbling spring”. Then the "e"
was droppped and in East Prussia, to where some people of that name
had immigrated (first records around 1650), the "D" changed to a
"T".
Then there is also: trespe, f. , ein unter dem getreide wachsendes
unkraut (Deutsches Wörterbuch von Jacob Grimm und Wilhelm Grimm)
and Triesch (Brache: unused farmland)
Scientific
Genealogy shows that
my academic ancestors are three Nobel prize winners (W. K.
Heisenberg, P. Debye, F. Bloch). Via advisors and co-advisors, my
academic lineage goes back to C. F. Gauß, and G. W.
Leibniz. Around 1983, my diploma co-advisors (Udo Kaatze)
organized a workshop together with Erwin Neher
who later wrote a recommendation letter for me for applying for a
stipend to attend a university in the U.S. In 1991,
Neher was awarded, along with Bert Sakmann, the Nobel Prize in
Physiology or Medicine for "their discoveries concerning the
function of single ion channels in cells" (
thepatch-clamp technique).
Around 1985, Eric Kandel
came to our flat after his talk at Yale discussing
neuroscience. Kandel won the 2000 Nobel Prize in Physiology
or Medicine for his research on the physiological basis of memory
storage in neurons. Reinhard Pottel and Udo Kaatze were my diploma
thesis advisors. My diploma thesis was a follow-up project of the
amazing PhD project of Eberhard Asselborn. In addition to physics,
Eberhard studied medicine and became an Ophthalmologist. His
reasoning for turning to medicine was that he did not think his
purpose in life was to build smart refrigerators. My PhD advisors
were Art Gmitro and Gene Gindi.