Generative models, especially diffusion models (DMs), have achieved promising results for
generating feature-rich geometries and advancing foundational science problems such as …

Symmetry-based neural networks often constrain the architecture in order to achieve
invariance or equivariance to a group of transformations. In this paper, we propose an …

Recent progress has been made towards learning invariant or equivariant representations
with self-supervised learning. While invariant methods are evaluated on large scale …

Learning visual features from unlabeled images has proven successful for semantic
categorization, often by mapping different views of the same object to the same feature to …

Abstract Machine learning for differential equations paves the way for computationally
efficient alternatives to numerical solvers, with potentially broad impacts in science and …

We introduce a general method for learning representations that are equivariant to
symmetries of data. Our central idea is to decompose the latent space into an invariant factor …

Theoretical and empirical comparisons have been made to assess the expressive power
and performance of invariant and equivariant GNNs. However, there is currently no …

Deep generative models have demonstrated successful applications in learning non-linear
data distributions through a number of latent variables and these models use a non-linear …

Although equivariant machine learning has proven effective at many tasks, success
depends heavily on the assumption that the ground truth function is symmetric over the …

Incorporating geometric inductive biases into models can aid interpretability and
generalization, but encoding to a specific geometric structure can be challenging due to the …