5 papers
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…
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…
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…
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…