Maximilian Thiessen

Maximilian Thiessen

PhD student in machine learning

TU Wien

Hi!

My name is Max. I am a PhD student supervised by Prof. Thomas Gärtner in the machine learning research unit at TU Wien, Austria. Before that, I studied computer science at the University of Bonn under the supervision of Dr. Tamás Horváth. My main research interest is active and semi-supervised learning. The goal is to achieve novel sample and query complexity bounds for learning tasks on graphs using convexity theory. Additionally, I am working on graph representations that go beyond the Weisfeiler-Leman isomorphism test.

Interests
  • Machine Learning
  • Active Learning
  • (Metric) Graph Theory
Education

  • PhD in Computer Science, 2020 — Present

    TU Wien, Austria

  • MSc in Computer Science, 2020

    University of Bonn, Germany

  • BSc in Computer Science, 2017

    University of Bonn, Germany

News

[Oct 2022] Happy to be recognised as a top reviewer (top 8%) of NeurIPS!

[Oct 2022] Two workshop papers accepted at GLFrontiers@NeurIPS (with Pascal Welke and Thomas Gärtner) and NeurReps@NeurIPS (with Sohir Maskey, Ali Parviz, Hannes Stärk, Ylli Sadikaj, and Haggai Maron)!

[Sep 2022] Together with Marco Bressan, Andrea Paudice, Nicolò Cesa-Bianchi (University of Milan), and Silvio Lattanzi (Google) we got our paper “Active Learning of Classifiers with Label and Seed Queries” accepted to NeurIPS 2022!

[Jul 2022] Happy to be recognised as an outstanding reviewer (top 10%) of ICML!

[Jul 2022] My colleague Fabian Jogl got our paper “Weisfeiler and Leman Return with Graph Transformations” accepted to MLG@ECMLPKDD 2022 and won the (community-voted) best poster award.

[Jul 2022] Passed my proficiency evaluation (mid-evaluation for PhD studies).

[Jul 2022] I attended the LogML 2022 summer school.

[Jul 2022] Together with a team lead by my colleague Tamara Drucks, we organised machine learning courses for children at the KinderUni Wien.

[Jul 2022] I got invited to serve as a reviewer for the Machine Learning journal, the LoG conference, and LWDA.

[Jun 2022] Our paper “Online Learning of Convex Sets on Graphs” got accepted to ECMLPKDD 2022!

[Jun 2022] I visited Marco Bressan and Nicolò Cesa-Bianchi at the University of Milan.

[Mai 2022] We are organising the Mining and Learning with Graphs workshop (MLG) at ECMLPKDD in Grenoble. Submit your work!

[Mai 2022] I attended the Hausdorff School on Algorithmic Data Analysis at University of Bonn.

[Apr 2022] I got invited to and attended G-Research’s Spring Insights Week.

[Mar 2022] Our master’s thesis student Fabian Jogl got his paper “Reducing Learning on Cell Complexes to Graphs” accepted to GTRL@ICLR 2022.

[Mar 2022] I got invited to serve as a reviewer for ICML, NeurIPS, and ECMLPKDD.

[Sep 2021] Our paper “Active Learning of Convex Halfspaces on Graphs” got
accepted to NeurIPS 2021!

[Sep 2021] I attended the Ellis Doctoral Symposium EDS 2021.

[Aug 2021] I attended Taipei’s MLSS 2021 and won a best poster honorable mention!

[Jul 2021] In a team with David Penz and Joe Redshaw, we won Siemens’ AI Dependability Assessment challenge with the best practical result!

[Jul 2021] I attended the LogML 2021 summer school.

[Jul 2021] I attended the EEML 2021 summer school.

Publications

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

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

Cite

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

Cite

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

PDF Cite Workshop Fabian Jogl

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

PDF Cite Video

Maximilian Thiessen, Thomas Gärtner (2021). Active Learning Convex Halfspaces on Graphs. SubSetML workshop at ICML.

PDF Cite Code Video Workshop

Thomas Schmied, Maximilian Thiessen (2020). Efficient Reinforcement Learning via Self-supervised learning and Model-based methods. RWRL workshop at NeurIPS.

PDF Cite Video Thomas Schmied

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

PDF Cite Code Slides Video

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

PDF Cite Code Video

Maximilian Thiessen (2020). Active Learning on Convex Subgraphs with Shortest Path Covers. M.Sc. thesis, University of Bonn.

PDF Cite Code

Experience

 
 
 
 
 
University Assistant
TU Wien
May 2020 – Present Vienna, Austria
Teaching assistant for various machine learning courses.
 
 
 
 
 
Research Assistant
Fraunhofer IAIS
Oct 2016 – Apr 2020 Sankt Augustin, Germany
Credit card fraud detection with subgroup discovery.
 
 
 
 
 
Tutor
University of Bonn
Oct 2018 – Mar 2020 Bonn, Germany
Tutor for graduate machine learning lectures.
 
 
 
 
 
Visiting Research Student
University College Cork
Aug 2019 – Aug 2019 Cork, Irelland
Research on local search and constraint programming.
 
 
 
 
 
Visiting Research Student
University of Nottingham
Aug 2018 – Sep 2018 Nottingham, England
Research on graph-based active learning and multiple systems estimation.
 
 
 
 
 
Software Developer Intern
T-Systems
Aug 2015 – Sep 2016 Bonn, Germany
Java development for customer relationship management software.

Contact