6 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…
MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models
Kacper KapuÅniak, Cristian Gabellini, Michael Bronstein +2
Molecular Dynamics (MD) is a powerful computational microscope for probing protein functions. However, the need for fine-grained integration and the long timescales of biomolecular…
Relaxed Equivariance via Multitask Learning
Ahmed A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni +1
Incorporating equivariance as an inductive bias into deep learning architectures to take advantage of the data symmetry has been successful in multiple applications, such as chemis…
Supercharging Graph Transformers with Advective Diffusion
Qitian Wu, Chenxiao Yang, Kaipeng Zeng +1
The capability of generalization is a cornerstone for the success of modern learning systems. For non-Euclidean data, e.g., graphs, that particularly involves topological structure…
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
Nian Liu, Xiaoxin He, Thomas Laurent +3
Spectral graph convolution, an important tool of data filtering on graphs, relies on two essential decisions: selecting spectral bases for signal transformation and parameterizing…
Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
Joshua Southern, Francesco Di Giovanni, Michael Bronstein +1
While message passing neural networks (MPNNs) have convincing success in a range of applications, they exhibit limitations such as the oversquashing problem and their inability to…