Learning-on-Graphs Conference 2023: Local Meetup

Local Meetup @ Munich

We are happy to have been accepted as a local meetup for the Learning-on-Graphs Conference 2023 and look forward to welcoming you to Munich this autumn! The following information sketches our schedule for a 2-day meetup. At this point, we are at capacity and unfortunately unable to accept further registrations. However, if you would like to join and had your paper accepted at LoG 2023, please reach out to emmelie.korell@tum.de.


November 30 & December 1, 2023


November 30

Time Program Location
15:00 Arrival & Registration IAS TUM
16:00 Orals (Livestream) IAS TUM
17:00 Keynote Prof. Kyle Cranmer (Livestream) IAS TUM
18:00 Tutorials (Livestream) & Networking & Fingerfood MDSI TUM
21:00 Closing Remarks MDSI TUM


Dezember 1

Time Program Location
10:00 Opening IAS TUM

Keynote Prof. Christopher Morris

Expressivity and Generalization Abilities of Graph Neural Networks

11:15 Talks I IAS TUM
12:30 Lunch Break MDSI TUM
13:30 Panel Discussion IAS TUM
14:30 Talks II IAS TUM
15:30 Poster Session MDSI TUM

Attendees are invited to extend their stay for further networking.


Slot 1: Friday, Dec 1, 11:15-12:30

Name Talk Title
Alice Moallemy-Oureh Graph Neural Networks for Attributed Dynamic Graphs in Continuous-Time Representation
Marco Sälzer Should We Aim for Sound and Complete Verification for GNN
Sayed Soroush Haj Zargarbashi Conformal Prediction for Graph Neural Networks
Chester Tan The Map Equation Goes Neural
Gianluca Galletti LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

Slot 2: Friday, Dec 1, 14:30-15:30

Name Talk Title
Jan Tönshoff Where Did the Gap Go? Reassessing LRGB
Nimrah Mustafa Are GATs Out of Balance?
Chirag Varun Shukla Towards Training GNNs using Explanation Directed Message Passing
Vincent Grande Topological Point Cloud Clustering: The Hodge Laplacian and Continuous Representations of Persistent Homology


The poster session is scheduled for Friday, Dec 1, 15:30. Posters may be brought, put up & admired already on Thursday afternoon.

Presenters Poster Title Authors
Jan Schuchardt (Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More Jan Schuchardt, Yan Scholten, Stephan Günnemann
Sohir Maskey  A Fractional Graph Laplacian Approach to Oversmoothing Sohir Maskey, Raffaele Paolino, Aras Bacho, Gitta Kutyniok
Artur Toshev Accelerating Molecular Graph Neural Networks via Knowledge Distillation Filip Ekström Kelvinius, Dimitar Georgiev, Artur Toshev, Johannes Gasteiger
Mahalakshmi Sabanayagam Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar
Nimrah Mustafa Are GATs Out of Balance?  Nimrah Mustafa, Aleksandar Bojchevski, Rebekka Burkholz
Vincenzo Perri Bayesian Detection of Mesoscale Structures in Pathway Data on Graphs Vincenzo Perri, Luka V. Petrović
Linlin Jia Bridging Distinct Spaces in Graph-Based Machine Learning Linlin Jia, Xiao Ning, Benoit Gaüzère, Paul Honeine, Kaspar Riesen
Sayed Soroush Haj Zargarbashi Conformal Prediction for Graph Neural Networks Soroush H. Zargarbashi, Aleksandar Bojchevski 
Nguyen Khoa Tran Drug Response Prediction using Multi-Omics Data and Molecular Graphs Nguyen Khoa Tran, Gunnar W. Klau
Chendi Qian Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems Chendi Qian, Didier Chételat, Christopher Morris
Andrei-Dragos Brasoveanu, Pascal Welke Extending Graph Neural Networks with Global Features  
Luca Verginer Forecasting Innovation with GRUs & Patent Embeddings Luca Verginer
Patrick Indri GraphPrivatizer: Improved Structural Differential Privacy for Graph Neural Networks Rucha Bhalchandra Joshi, Patrick Indri, Subhankar Mishra
Alice Moallemy-Oureh Handling of Attribute Dynamics in Graph Learning Alice Moallemy-Oureh
Christian Koke HoloNets: Spectral Convolutions do extend to Directed Graphs  Christian Koke, Daniel Cremers
Gianluca Galletti LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite Artur P. Toshev, Gianluca Galletti, Fabian Fritz, Stefan Adami, Nikolaus A. Adams
Rebekka Burkholz Learning on random graphs Advait Gadhikar, Nimrah Mustafa, Adarsh Jamadandi, Rebekka Burkholz
Vincent Grande Non-Isotropic Persistent Homology: Leveraging the Metric Dependency of PH  
Tamara Drucks PAN: Expressiveness of GNNs with Paths Caterina Graziani, Tamara Drucks, Monica Bianchini, Franco Scarselli, Thomas Gärtner
Andreas Roth Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks Andreas Roth, Thomas Liebig
Jonas Jürß Recursive Algorithmic Reasoning Jonas Jürß, Dulhan Jayalath, Petar Velickovic
Sadegh Akhondzadeh Rethinking Label Poisoning for GNNs: Pitfalls and Attacks  
Lukas Gosch Revisiting Robustness in Graph Machine Learning Lukas Gosch, Simon Geisler, Daniel Sturm, Stephan Günnemann
Florian Grötschla SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning Julian Minder, Florian Grötschla, Joel Mathys, Roger Wattenhofer
Christopher Blöcker Sampling Networks from Modular Compression of Network Flows  Christopher Blöcker, Jelena Smiljanić, Martin Rosvall, Ingo Scholtes
Vincent Stimper SE(3) Equivariant Augmented Coupling Flows Laurence I Midgley, Vincent Stimper, Javier Antorán, Emile Mathieu, Bernhard Schölkopf, José Miguel Hernández-Lobato
Marco Sälzer Sound and Complete Verification of GNN Marco Sälzer and Martin Lange
Silvia Beddar-Wiesing Structural-Dynamic Graph Embedding Silvia Beddar-Wiesing
Joël Mathys SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics Stefan Künzli, Florian Grötschla, Joël Mathys, Roger Wattenhofer
Chester Tan The Map Equation Goes Neural Christopher Blöcker, Chester Tan, Ingo Scholtes
Moritz Lampert The Self-loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks Moritz Lampert, Ingo Scholtes
Leon Klein Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde, Bruno Mlodozeniec, Marc Brockschmidt, Sebastian Nowozin, Frank Noé, Ryota Tomioka
Vincent Grande Topological Point Cloud Clustering: The Hodge Laplacian and Continuous Representations of Persistent Homology Vincent P. Grande, Michael T. Schaub
Luis Müller, Frederik Wenkel, Blazej Banaszewski Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets Dominique Beaini, Shenyang Huang, Joao Alex Cunha, Gabriela Moisescu-Pareja, Oleksandr Dymov, Samuel Maddrell-Mander, Callum McLean, Frederik Wenkel, Luis Müller, Jama Hussein Mohamud, Ali Parviz, Michael Craig, Michał Koziarski, Jiarui Lu, Zhaocheng Zhu, Cristian Gabellini, Kerstin Klaser, Josef Dean, Cas Wognum, Maciej Sypetkowski, Guillaume Rabusseau, Reihaneh Rabbany, Jian Tang, Christopher Morris, Mirco Ravanelli, Guy Wolf, Prudencio Tossou, Hadrien Mary, Therence Bois, Andrew Fitzgibbon, Błażej Banaszewski, Chad Martin, Dominic Masters
Chirag Varun Shukla Towards Training GNNs using Explanation Directed Message Passing Valentina Giunchiglia, Chirag Varun Shukla, Guadalupe Gonzalez, Chirag Agarwal
Tom Wollschläger Uncertainty Estimation for Molecules Tom Wollschläger, Nicholas Gao, Betrand Charpentier, Amine Ketata, Stephan Günnemann
Dominik Fuchsgruber Uncertainty for Active Learning on Graphs Dominik Fuchsgruber, Tom Wollschläger, Bertrand Charpentier, Antonio Oroz, Stephan Günnemann
Franziska Heeg Using Causality-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs Franziska Heeg, Ingo Scholtes
Martin Ritzert, Eran Rosenbluth, Jan Tönshoff Where did the gap go? Reassessing LRGB Jan Tönshoff, Martin Ritzert, Eran Rosenbluth, and Martin Grohe (both not attending)
Pascal Welke Maximally Expressive GNNs for Outerplanar Graphs  

Location: IAS & MDSI

The meetup takes place at TUM Institute for Advanced Studies (IAS) and TUM Munich Data Science Institue (MDSI).

Lichtenbergstraße 2 a
85748 Garching

Walther-von-Dyck-Str. 10
85748 Garching


Stephan Günnemann

Technische Universität München

Bastian Rieck

Helmholtz Munich

Ingo Scholtes

Julius-Maximilians-Universität Würzburg

Related Research: InterConnect

Graph neural networks and topological data analysis provide strong potential for gaining deeper insights into global patterns in graph-structured data, utilizing a combination of ML, combinatorics, geometry, algebra, and statistics techniques. Studying these networks’ connectivity provides insights into information flow, social dynamics, disease spread, traffic optimization, network resilience, and much more. 

Closely related to the concerns of the Learning on Graphs conference, the new MDSI focus topic InterConnect: Interdisciplinary Research on Graphs, Networks, and Connectivity Structures tackles similar topics. If you are interested, please take a look at the focus topic!