You are here: Home → People → Dr. Pascal Welke

Dr. Pascal Welke

I am interested in Data Mining, Applied Graph Theory, Machine Learning, and Human-computer Interaction. I wrote my PhD thesis on 'Probabilistic Frequent Subtree Mining'.

I also teach several courses that are offered by our group in the Bachelors program and Masters program in Computer Science and I supervise BA and MA theses.

 

Contact

University of Bonn:

Phone: +49 228 73 4514

Room 1.027
Friedrich-Hirzebruch-Allee 8

Please send snail mail to
Friedrich-Hirzebruch-Allee 5
53115 Bonn

email: 
[Email protection active, please enable JavaScript.]
 
Other:
I have an account on ResearchGate.  My publications are indexed by dblp and google scholar. Some of the code that I write is on github.
You can give me anonymous feedback (for example on my teaching performance).

Current Preprints

  1. Vanessa Toborek, Moritz Busch, Malte Boßert, Christian Bauckhage, Pascal Welke:
    A New Aligned Simple German Corpus
    CoRR abs/2209.01106

    [preprint] [openreview] [code]

  2. Richard Palme, Pascal Welke:
    Frequent Generalized Subgraph Mining via Graph Edit Distances. (accepted at SEDAMI2022@ECMLPKDD)

    [preprint] [code]

  3. Katharina Beckh, Sebastian Müller, Matthias Jakobs, Vanessa Toborek, Hanxiao Tan, Raphael Fischer, Pascal Welke, Sebastian Houben, Laura von Rueden:
    Explainable Machine Learning with Prior Knowledge: An Overview
    CoRR abs/2105.10172

    [preprint] [dblp]

  4. Ramsés J. Sánchez, Lukas Conrads, Pascal Welke, Kostadin Cvejoski, César Ojeda:
    Hidden Schema Networks
    CoRR abs/2207.03777

    [preprint]

Publications

  1. Till Schulz, Pascal Welke, Stefan Wrobel:
    Graph Filtration Kernels.
    AAAI Conference on Artificial Intelligence, 36(8), 2022.

    [preprint] [code] [poster] [slides] [arxiv] [dblp] [doi (open access)] [conference]

  2. Dario Antweiler, Marc Harmening, Nicole Marheineke, Andre Schmeißer, Raimund Wegener, Pascal Welke:
    Machine Learning Framework to predict Nonwoven Material Properties from Fiber Graph Representations.
    Software Impacts, Volume 14, Elsevier, 2022.

    [code] [reproducible run] [doi (open access)] [dblp] [journal]

  3. Till Schulz, Tamas Horvath, Pascal Welke, Stefan Wrobel:
    A Generalized Weisfeiler-Lehman Graph Kernel.
    Machine Learning, Volume 111, Issue 7, Springer, 2022.

    [preprint] [code] [doi (open access)] [dblp] [arXiv] [journal]

  4. Dario Antweiler, Marc Harmening, Nicole Marheineke, Andre Schmeißer, Raimund Wegener, Pascal Welke:
    Graph-Based Tensile Strength Approximation of Random Nonwoven Materials by Interpretable Regression.
    Machine Learning with Applications, Volume 8, Elsevier, 2022.

    [code] [reproducible run] [doi (open access)] [dblp] [journal]

  5. Janis Kalofolias, Pascal Welke, Jilles Vreeken:
    SUSAN: The Structural Similarity Random Walk Kernel.
    SIAM International Conference on Data Mining, SDM, 2021.

    [preprint] [slides] [video] [doi] [dblp] [conference]

  6. Pascal Welke, Fouad Alkhoury, Christian Bauckhage, Stefan Wrobel:
    Decision Snippet Features.
    International Conference on Pattern Recognition, ICPR, 2021.

    [preprint] [code] [video] [slides] [doi] [dblp] [conference]

  7. Dario Antweiler, Pascal Welke:
    Temporal Graph Analysis for Outbreak Pattern Detection in COVID-19 Contact Tracing Networks.
    Machine Learning in Public Health Workshop, MLPH@NeurIPS, 2020.

    [preprint] [slides] [workshop]

  8. Pascal Welke:
    Efficient Frequent Subgraph Mining in Transactional Databases.
    IEEE International Conference on Data Science and Advanced Analytics, DSAA, 2020.

    [preprint] [video] [slides] [doi] [dblp] [conference]

  9. Pascal Welke, Florian Seiffarth, Michael Kamp, Stefan Wrobel:
    HOPS: Probabilistic Subtree Mining for Small and Large Graphs.
    ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD, 2020.

    [preprint] [code] [short video] [slides] [video] [doi] [dblp] [conference]

  10. Alexander Mehler, Wahed Hemati, Pascal Welke, Maxim Konca, Tolga Uslu:
    Multiple Texts as a Limiting Factor in Online Learning: Quantifying (Dis-)similarities of Knowledge Networks across Languages.
    Frontiers in Education | Digital Education, 2020.

    [preprint] [doi (open access)] [dblp] [arXiv] [journal]

  11. Till Schulz, Pascal Welke:
    On the Necessity of Graph Kernel Baselines.
    Graph Embedding and Mining Workshop, GEM@ECMLPKDD, 2019.

    [paper] [poster] [workshop]

  12. Pascal Welke:
    Frequent Subtree Mining Beyond Forests.
    Dissertations in Artificial Intelligence Vol. 348, IOS Press, 2019.

    [pdf] [slides] [urn] [official publication venue] [dblp] [book]

  13. Pascal Welke, Tamas Horvath, Stefan Wrobel:
    Probabilistic and Exact Frequent Subtree Mining in Graphs Beyond Forests.
    Machine Learning, Volume 108, Issue 7, 2019

    [preprint] [doi] [read-only free official version] [dblp] [journal]

  14. Pascal Welke, Tamas Horvath, Stefan Wrobel:
    Probabilistic Frequent Subtrees for Efficient Graph Classification and Retrieval.
    Machine Learning, Volume 107, Issue 11, Springer, 2018.

    [preprint] [dblp] [doi] [read-only free official version] [journal]

  15. Till Schulz, Tamas Horvath, Pascal Welke, Stefan Wrobel:
    Mining Tree Patterns with Partially Injective Homomorphisms.
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD, Springer LNCS 11052, 2018.

    [preprint] [slides] [dblp] [doi] [conference]
  16. Pascal Welke:
    Simple Necessary Conditions for the Existence of a Hamiltonian Path with Applications to Cactus Graphs.
    CoRR abs/1709.01367, 2017.

    [preprint] [slides] [arXiv] [workshop]
  17. Pascal Welke, Alexander Markowetz, Torsten Suel, Maria Christoforaki:
    3-Hop Distance Estimation in Social Graphs.
    IEEE International Conference on Big Data, BigData, IEEE, 2016.

    [preprint] [slides] [dblp] [doi] [conference]
  18. Pascal Welke, Tamas Horvath, Stefan Wrobel:
    Min-Hashing for Probabilistic Frequent Subtree Feature Spaces.
    Proceedings of Discovery Science - 18th International Conference, DS, Springer LNAI 9956, 2016.

    [preprint] [slides] [poster] [dblp] [doi] [conference]
  19. Katrin Ullrich, Jennifer Mack, Pascal Welke:
    Ligand Affinity Prediction with Multi-Pattern Kernels.
    Proceedings of Discovery Science - 18th International Conference, DS, Springer LNAI 9956, 2016.

    [preprint] [slides] [dblp] [doi] [conference]
  20. Pascal Welke, Ionut Andone, Konrad Blaskiewicz, Alexander Markowetz:
    Differentiating Smartphone Users by App Usage.
    Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp, ACM, 2016.

    [preprint] [slides] [dblp] [doi] [conference]
  21. Pascal Welke, Tamas Horvath, Stefan Wrobel:
    Probabilistic Frequent Subtree Kernels.
    Proceedings of the Fourth Workshop on New Frontiers in Mining Complex Patterns, nfMCP@ECMLPKDD, Selected Extended Papers, Springer LNCS 9607, 2015.

    [preprint] [slides] [dblp] [doi] [workshop]
  22. Pascal Welke, Tamas Horvath, Stefan Wrobel:
    On the Complexity of Frequent Subtree Mining in Very Simple Structures.
    Proceedings of the Inductive Logic Programming Conference, ILP, Springer LNCS 9046, 2014.

    [preprint] [slides] [dblp] [doi] [conference]
  23. Anne-Kathrin Mahlein, Till Rumpf, Pascal Welke, Heinz-Wilhelm Dehne, Lutz Plümer, Ulrike Steiner, Erich-Christian Oerke:
    Development of spectral indices for detecting and identifying plant diseases.
    Remote Sensing of Environment Volume 128, Elsevier, 2013.

    [doi] [journal]

Lecture Notes and Coding Nuggets

  1. Pascal Welke and Christian Bauckhage
    Solving Linear Programming Problems

    This note discusses how to solve linear programming problems with SciPy. As a practical use case, we consider the task of computing the Chebyshev center of a bounded convex polytope.

  2. Pascal Welke and Christian Bauckhage
    Linear Programming for Robust Regression

    Having previously discussed how scipy allows us to solve linear programs, we can study further applications of linear programming. Here, we consider least absolute deviation regression and solve a simple parameter estimation problem deliberately chosen to expose potential pitfalls in using scipy's optimization functions.

  3. Christian Bauckhage and Pascal Welke
    Sorting as Linear Programming

    Linear programming is a surprisingly versatile tool. That is, many problems we would not usually think of in terms of a linear programming problem can actually be expressed as such. In this note, we show that sorting is such a problem and discuss how to solve linear programs for sorting using SciPy.

  4. Christian Bauckhage and Pascal Welke
    Sorting as Quadratic Unconstrained Binary Optimization Problem

    Having previously considered sorting as a linear programming problem, we now cast it as a quadratic unconstrained binary optimization problem (QUBO). Deriving this formulation is a bit cumbersome but it allows for implementing neural networks or even quantum computing algorithms that sort. Here, however, we consider a simple greedy QUBO solver and implement it using Numpy.

  5. Christian Bauckhage and Pascal Welke
    Centering Data- and Kernel Matrices

    We discuss the notion of centered data matrices and show how to compute them using centering matrices. As centering matrices have many applications in data science and machine learning, we have a look at one such application and discuss how they allow for centering kernel matrices.

  6. Pascal Welke, Till Hendrik Schulz, and Christian Bauckhage
    Computational Complexity of Max-Sum Diversification

    We show how max-sum diversification can be used to solve the $k$-clique problem, a well-known NP-complete problem. This reduction proves that max-sum diversification is NP-hard and provides a simple and practical method to find cliques of a given size using Hopfield networks.

  7. Christian Bauckhage and Pascal Welke
    Solving Least Squares Gradient Flows

    We approach least squares optimization from the point of view of gradient flows. As a practical example, we consider a simple linear regression problem, set up the corresponding differential equation, and show how to solve it using SciPy.

Community Activities

  1. We are organizing MLG@ECMLPKDD 2022, the 18th Workshop on Mining and Learning with Graphs.
  2. I am program chair of the KDML track at LWDA 2022.
  3. We have organized GEM'21, the third Workshop on Graph Embedding and Mining, collocated with ECMLPKDD'21! It has been a pleasure! Here are the proceedings.
  4. I am a member of the program committee of PDFL'21, the Workshop on Parallel, Distributed, and Federated Learning, collocated with ECMLPKDD'21. Here are the proceedings.
  5. I have co-organized GEM'20, Workshop on Graph Embedding and Mining, collocated with ECMLPKDD'20.
  6. I was program chair (with Nico Piatkowski) of the KDML track at LWDA 2020. It has been a pleasure. Here are the proceedings.
  7. Member of the program committee of PDFL'20, the Workshop on Parallel, Distributed, and Federated Learning, collocated with ECMLPKDD'20.
  8. Program committee member of ICLR'22, SISAP'21, ICML'21, AISTATS'20 '21 '22, SDM'21, ICDM'20, ECMLPKDD'20 '21, ICLR'21, and NeurIPS'20 '21.
  9. Member of the program committee of GEM'19, the Workshop on Graph Embedding and Mining, collocated with ECMLPKDD'19.
  10. Member of the program committee of DMLE'19, the Second Workshop on Distributed Machine Learning at the Edge, collocated with ECMLPKDD'19.
  11. Reviews for several journals, conferences, and academic funding programs, e.g. Machine Learning, Data Mining and Knowledge Discovery, AMAI, ACM SIGKDD 2016,  KI-Starter NRW.
Document Actions