_MG_3121Q small.jpg Email: lukas.pfahler At sign tu-dortmund.de
Phone: 0231/755-8229
Room-No.: JvF25 R119

Consultation hour:
Thursdays, 14-16h. Please send me an e-mail ahead of time.
During the semester break (solely by arrangement)


Lukas Pfahler has studied computer science at the TU Dortmund University, where he received his Master of Science degree with distinction. Since 2016 he is a research associate at the chair for artificial intelligence at the department of computer science. In 2022, he obtained his PhD for defending the dissertation "Some Representation Learning Tasks and the Inspection of Their Models"

PGP Key for Encrypted Email Communication

Research Interests

  • Statistical Learning Theory
  • Theoretical Foundations of Deep Network Learning
  • Representation Learning



  • Visually Inspecting Singular Values in Deep Networks (Abstract)
  • Generalization in Deep Networks -- A very short introduction (Abstract)
  • What do you do with 5 million posts?: Versuche zum distant reading religiöser Online-Foren (Abstract)

Social Media

bitbucket.org | github.com | linkedin.com




Buschjaeger/etal/2021a Buschjäger, Sebastian and Chen, Jian-Jia and Chen, Kuan-Hsun and Günzel, Mario and Hakert, Christian and Morik, Katharina and Novkin, Rodion and Pfahler, Lukas and Yayla, Mikail. Margin-Maximization in Binarized Neural Networks for Optimizing Bit Error Tolerance. In Proceedings of DATE 2021, 2021. Arrow Symbol
Buschjaeger/etal/2021b Buschjäger, Sebastian and Honysz, Philipp-Jan and Morik, Katharina. Very Fast Streaming Submodular Function Maximization (Extended Version). 2021. Arrow Symbol
Buschjaeger/etal/2021c Sebastian Buschjäger and Jian-Jia Chen and Kuan-Hsun Chen and Mario Günzel and Katharina Morik and Rodion Novkin and Lukas Pfahler and Mikail Yayla. Bit Error Tolerance Metrics for Binarized Neural Networks. 2021. Arrow Symbol
Haritz/etal/2021a Haritz, Pierre and Pfahler, Lukas and Liebig, Thomas and Kotthaus, Helena. Self-Supervised Source Code Annotation from Related Research Papers. In Proceedings of the PhD Forum of the 21st IEEE International Conference on Data Mining, pages 1083-1084, 2021.
Pfahler/etal/2021a Pfahler, Lukas and Bunse, Mirko and Morik, Katharina. Noisy Labels for Weakly Supervised Gamma Hadron Classification. 2021. Arrow Symbol
Pfahler/Morik/2021a Pfahler, Lukas and Morik, Katharina. Explaining Deep Learning Representations by Tracing the Training Process. 2021. Arrow Symbol
Buschjaeger/etal/2020a Buschjäger, Sebastian and Pfahler, Lukas and Buss, Jens and Morik, Katharina and Rhode, Wolfgang. On-Site Gamma-Hadron Separation with Deep Learning on FPGAs. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, 2020. Arrow Symbol
Buschjaeger/etal/2020b Buschjäger, Sebastian and Chen, Jian-Jia and Chen, Kuan-Hsun and Günzel, Mario and Hakert, Christian and Morik, Katharina and Novkin, Rodion and Pfahler, Lukas and Yayla, Mikail. Towards Explainable Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks. 2020. Arrow Symbol
Buschjaeger/etal/2020c Sebastian Buschjäger and Lukas Pfahler and Katharina Morik. Generalized Negative Correlation Learning for Deep Ensembling. 2020. Arrow Symbol
Pfahler/Morik/2020a Pfahler, Lukas and Morik, Katharina. Semantic Search in Millions of Equations. In KDD '20- Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, 2020. Arrow Symbol
Pfahler/Morik/2020b Pfahler, Lukas and Morik, Katharina. Fighting Filterbubbles with Adversarial Training. 2020.
Pfahler/Richter/2020a Lukas Pfahler and Jan Richter. Interpretable Nearest Neighbor Queries for Tree-Structured Data in Vector Databases of Graph-Neural Network Embeddings. In Alexandra Poulovassilis and David Auber and Nikos Bikakis and Panos K. Chrysanthis and George Papastefanatos and Mohamed A. Sharaf and Nikos Pelekis and Chiara Renso and Yannis Theodoridis and Karine Zeitouni and Tania Cerquitelli and Silvia Chiusano and Genoveva Vargas-Solar and Behrooz Omidvar-Tehrani and Katharina Morik and Jean-Michel Renders and Donatella Firmani and Letizia Tanca and Davide Mottin and Matteo Lissandrini and Yannis Velegrakis (editors), Proceedings of International Workshop on Explainability for Trustworthy ML Pipelines (ETMLP-2020), CEUR-WS.org, 2020. Arrow Symbol
Pfahler/etal/2019b Pfahler, Lukas and Schill, Jonathan and Morik, Katharina. The Search for Equations - Learning to Identify Similarities between Mathematical Expressions. In Procs. ECML PKDD2019, Springer, 2019. Arrow Symbol
Pfahler/Morik/2018a Pfahler, Lukas and Morik, Katharina. Nystroem-SGD: Rapidly Learning Kernel-Classifiers with Conditioned Stochastic Gradient Descent. In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2018, Dublin, Ireland, 2018.
Pfahler/etal/2017a Pfahler, Lukas and Morik, Katharina and Elwert, Frederik and Tabti, Samira and Krech, Volkhard. Learning Low-Rank Document Embeddings with Weighted Nuclear Norm Regularization. In Proceedings of the 4th IEEE International Conference on Data Science and Advanced Analytics, 2017.
Buschjaeger/etal/2015a Buschjäger, Sebastian and Pfahler, Lukas and Morik, Katharina. Discovering Subtle Word Relation in Large German Corpora. In Proceedings of the 3rd Workshop on the Challenges in the Management of Large Corpora, 2015. Arrow Symbol
Morik/etal/2015a Morik, Katharina and Jung, Alexander and Weckwerth, Jan and Rötner, Stefan and Hess, Sibylle and Buschjäger, Sebastian and Pfahler, Lukas. Untersuchungen zur Analyse von deutschsprachigen Textdaten. No. 2, Technische Universität Dortmund, 2015. Arrow Symbol
Pfahler/2015a Pfahler, Lukas. Explicit and Implicit Feature Maps for Structured Output Prediction. TU Dortmund, 2015.
Pfahler/2013a Pfahler, Lukas. Effizienteres k-means Clustering von Zeitreihen mit Dynamic Time Warping durch kaskadiertes Berechnen von unteren Schranken. 2013.


Thesis Proposals

Supervised Theses