5 papers · 1 filter
Riemannian Metric Matching for Scalable Geometric Modeling of Distributions
Jacob Bamberger, Adam Gosztolai, Pierre Vandergheynst +2
High-dimensional datasets often concentrate near low-dimensional structures, but estimating their geometry from samples typically relies on graphs and kernels that scale poorly wit…
Carré du champ flow matching: better quality-generalisation tradeoff in generative models
Jacob Bamberger, Iolo Jones, Dennis Duncan +3
Deep generative models often face a fundamental tradeoff: high sample quality can come at the cost of memorisation, where the model reproduces training data rather than generalisin…
On Measuring Long-Range Interactions in Graph Neural Networks
Jacob Bamberger, Benjamin Gutteridge, Scott le Roux +2
Long-range graph tasks -- those dependent on interactions between distant nodes -- are an open problem in graph neural network research. Real-world benchmark tasks, especially the…
Over-squashing in Spatiotemporal Graph Neural Networks
Ivan Marisca, Jacob Bamberger, Cesare Alippi +1
Graph Neural Networks (GNNs) have achieved remarkable success across various domains. However, recent theoretical advances have identified fundamental limitations in their informat…
Bundle Neural Networks for message diffusion on graphs
Jacob Bamberger, Federico Barbero, Xiaowen Dong +1
The dominant paradigm for learning on graph-structured data is message passing. Despite being a strong inductive bias, the local message passing mechanism suffers from pathological…