4 papers
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
Alan Muriithi, Vedanta Thapar, Torben Berndt
When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter space realising the group actio…
Universal Time Series Generation with Neural Controlled Differential Equations
Torben Berndt, Elyes Farjallah, Leif Seute +3
Recent work on the sequence universality of State Space Models (SSMs) has introduced efficient, maximally expressive continuous-time approaches for time-series modelling. While the…
Approximate Equivariance via Projection-based Regularisation
Torben Berndt, Jan Stühmer
Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention,…
Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
Torben Berndt, Benjamin Walker, Tiexin Qin +2
Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential…