activity
20212024
most citedTowards a General Purpose CNN for Long Range Dependencies in D

9 citations · 12 across the 10 of their papers we have counts for

collaborators

10 papers

cs.LG2024

E(n) Equivariant Message Passing Cellular Networks

Veljko Kovač, Erik J. Bekkers, Pietro Liò +1

This paper introduces E(n) Equivariant Message Passing Cellular Networks (EMPCNs), an extension of E(n) Equivariant Graph Neural Networks to CW-complexes. Our approach addresses tw…

cs.LG20241 cited

The Hidden Pitfalls of the Cosine Similarity Loss

Andrew Draganov, Sharvaree Vadgama, Erik J. Bekkers

We show that the gradient of the cosine similarity between two points goes to zero in two under-explored settings: (1) if a point has large magnitude or (2) if the points are on op…

cs.LG2024

Space-Time Continuous PDE Forecasting using Equivariant Neural Fields

David M. Knigge, David R. Wessels, Riccardo Valperga +4

Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF. Althou…

cs.LG2023

Can strong structural encoding reduce the importance of Message Passing?

Floor Eijkelboom, Erik Bekkers, Michael Bronstein +1

The most prevalent class of neural networks operating on graphs are message passing neural networks (MPNNs), in which the representation of a node is updated iteratively by aggrega…

cs.LG2023

On genuine invariance learning without weight-tying

Artem Moskalev, Anna Sepliarskaia, Erik J. Bekkers +1

In this paper, we investigate properties and limitations of invariance learned by neural networks from the data compared to the genuine invariance achieved through invariant weight…

cs.CV20231 cited

Learned Gridification for Efficient Point Cloud Processing

Putri A. van der Linden, David W. Romero, Erik J. Bekkers

Neural operations that rely on neighborhood information are much more expensive when deployed on point clouds than on grid data due to the irregular distances between points in a p…