11 citations · 14 across the 4 of their papers we have counts for
5 papers
A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting
Michael Banf, Dominik Filipiak, Max Schattauer +1
Graph Neural Networks are highly effective at learning from relational data, leveraging node and edge features while maintaining the symmetries inherent to graph structures. Howeve…
Comparison of Three Methods for Triggering Core-collapse Supernova Explosions in Spherical Symmetry
Liliya Imasheva, H. -Thomas Janka, Achim Weiss
Despite the three-dimensional nature of core-collapse supernovae (CCSNe), simulations in spherical symmetry (1D) play an important role to study large model sets for the progenitor…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
TopoBench: A Framework for Benchmarking Topological Deep Learning
Lev Telyatnikov, Guillermo Bernardez, Marco Montagna +34
This work introduces TopoBench, an open-source library designed to standardize benchmarking and accelerate research in topological deep learning (TDL). TopoBench decomposes TDL int…
Parameterisations of thermal bomb explosions for core-collapse supernovae and 56Ni production
Liliya Imasheva, H. -Thomas Janka, Achim Weiss
Thermal bombs are a widely used method to artificially trigger explosions of core-collapse supernovae (CCSNe) to determine their nucleosynthesis or ejecta and remnant properties. R…