Maximilian Thiessen

Hey there, my name is Max. I am a PhD student supervised by Thomas Gärtner in the machine learning research unit at TU Wien. Before that, I studied computer science at the University of Bonn under the supervision of Tamás Horváth. My main research areas are learning with graphs, active learning, and learning theory. I try to bridge (graph) convexity theory and learning theory. More recently I have started working on graph representations learning and graph neural networks.

  1. News
  2. Publications
  3. Workshop Papers
  4. Community Activities
  5. People
  6. Contact

News

[Mar '24]Visited Marco Bressan and Nicolò Cesa-Bianchi at the University of Milan supported by an ELLIS / ELISE travel grant.
[Mar '24]We are organising the Mining and Learning with Graphs workshop (MLG) at ECMLPKDD in Vilnius. Submit your work!
[Nov '23]Happy to receive a DOC fellowship of the Austrian Academy of Sciences (ÖAW) to continue my PhD studies for two more years!
[Nov '23]Two papers accepted at the 2nd LoG conference with Franka Bause (Uni Vienna), Andrei Brasoveanu, Fabian Jogl, and Pascal Welke.
[Nov '23]Happy to be again recognised as a top reviewer of NeurIPS.
[Oct '23]Together with Franka Bause (Uni Vienna), Fabian Jogl, Patrick Indri, Tamara Drucks, David Penz, Nils Kriege (Uni Vienna), Thomas Gärtner, and Pascal Welke we got our paper Maximally Expressive GNNs for Outerplanar Graphs accepted as an oral at GLFrontiers@NeurIPS.
[Sep '23]Together with Fabian Jogl and Thomas Gärtner we got our paper Expressivity-Preserving GNN Simulation accepted to NeurIPS '23!
[Jul '23]I won a best poster award at G-Research's ICML poster party in London.
[Mai '23]Together with Pascal Welke, Fabian Jogl, and Thomas Gärtner we got our paper Expectation-Complete Graph Representations with Homomorphisms accepted to ICML '23!
[Feb '23]We are organising the 1st Community event for machine learning PhD students in Vienna (C’Est La Wien)!

Publications

  1. Expressivity-Preserving GNN Simulation
    Fabian Jogl, Maximilian Thiessen, Thomas Gärtner
    NeurIPS (2023)

    [conference]

  2. Expectation-Complete Graph Representations with Homomorphisms
    Pascal Welke*, Maximilian Thiessen*, Fabian Jogl, Thomas Gärtner
    ICML (2023)

    [pdf] [poster] [slides] [video] [code] [reviews] [arXiv] [conference]

  3. Active Learning of Classifiers with Label and Seed Queries
    Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice, Maximilian Thiessen
    NeurIPS (2022)

    [video] [arXiv] [conference]

  4. Online Learning of Convex Sets on Graphs
    Maximilian Thiessen, Thomas Gärtner
    ECMLPKDD (2022)

    [pdf] [conference]

  5. Active Learning of Convex Halfspaces on Graphs
    Maximilian Thiessen, Thomas Gärtner
    NeurIPS (2021)

    [pdf] [slides] [video] [code] [reviews] [conference]

  6. Improving a Branch-and-Bound Approach for the Degree-Constrained Minimum Spanning Tree Problem with LKH
    Maximilian Thiessen, Luis Quesada, Kenneth N Brown
    CPAIOR (2020)

    [video] [conference]

Workshop Papers and Extended Abstracts

  1. Maximally Expressive GNNs for Outerplanar Graphs
    Franka Bause, Fabian Jogl, Patrick Indri, Tamara Drucks, David Penz, Nils Kriege, Thomas Gärtner, Pascal Welke, Maximilian Thiessen
    GLFrontiers@NeurIPS (2023)

    [workshop]

  2. Extending Graph Neural Networks with Global Features
    Andrei Dragos Brasoveanu*, Fabian Jogl*, Pascal Welke, Maximilian Thiessen
    LoG (2023)

    [workshop]

  3. Maximally Expressive GNNs for Outerplanar Graphs
    Franka Bause*, Fabian Jogl*, Pascal Welke, Maximilian Thiessen
    LoG (2023)

    [workshop]

  4. Generalized Laplacian Positional Encoding for Graph Representation Learning
    Sohir Maskey, Ali Parviz, Maximilian Thiessen, Hannes Stärk, Ylli Sadikaj, Haggai Maron
    NeurReps@NeurIPS (2022)

    [pdf] [reviews] [arXiv] [workshop]

  5. Expectation Complete Graph Representations using Graph Homomorphisms
    Pascal Welke*, Maximilian Thiessen*, Thomas Gärtner
    LoG (2022)

    [pdf] [poster] [code] [reviews] [conference]

  6. Expectation Complete Graph Representations using Graph Homomorphisms
    Maximilian Thiessen*, Pascal Welke*, Thomas Gärtner
    GLFrontiers@NeurIPS (2022)

    [pdf] [poster] [code] [reviews] [workshop]

  7. Weisfeiler and Leman Return with Graph Transformations
    Fabian Jogl, Maximilian Thiessen, Thomas Gärtner
    MLG@ECMLPKDD (2022)

    [pdf] [workshop]

  8. Reducing Learning on Cell Complexes to Graphs
    Fabian Jogl, Maximilian Thiessen, Thomas Gärtner
    GTRL@ICLR (2022)

    [pdf] [reviews] [workshop]

  9. Active Learning Convex Halfspaces on Graphs
    Fabian Jogl, Maximilian Thiessen, Thomas Gärtner
    SubSetML@ICML (2021)

    [pdf] [video] [code] [workshop]

  10. Active Learning on Graphs with Geodesically Convex Classes
    Maximilian Thiessen, Thomas Gärtner
    MLG@KDD (2020)

    [pdf] [video] [code] [workshop]

Community Activities

  1. Program committee member/reviewer at conferences: NeurIPS21'22*'23*, ICML'22*'23'24, ICLR'24, ECMLPKDD'22'23*'24, LOG'22'23, and LWDA'22.
  2. Regular reviewer for MLJ and the ECMLPKDD journal track (2023).
  3. Organizer of MLG@ECMLPKDD 2022, 2023, and 2024, the 18th, 20th, and 22nd Workshop on Mining and Learning with Graphs.
  4. Initiator and organizer of C'Est La Wien '23, the Community Event for Students of Learning Algorithms in Wien.
  5. Session chair at ECMLPKDD'23.
  6. Co-organizer of a machine learning course for children at the KinderUni Wien (2022).
(* means top reviewer)

People

Frequent collaborators and colleagues

Contact

You can find me on Twitter, Github, LinkedIn, and Google scholar.

Office: 2nd Floor, Erzherzog-Johann-Platz 1 (FB02), 1040 Vienna, Austria.
Email: You can send mail to maximilian.thiessen@tuwien.ac.at.

This page is blatantly copied from my lovely colleague Pascal Welke. It tries to be minimalistic in layout, bandwith, and used tools. It is hosted on Github pages, using neat.css stylesheets, and bibtexparser to generate the lists of references.