Arguably one of the top success stories of deep learning is transfer learning. The finding that
pre-training a network on a rich source set (eg, ImageNet) can help boost performance once …

Effectively predicting molecular interactions has the potential to accelerate molecular
dynamics by multiple orders of magnitude and thus revolutionize chemical simulations …

We show that standard Transformers without graph-specific modifications can lead to
promising results in graph learning both in theory and practice. Given a graph, we simply …

Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which
model graphs as collections of subgraphs. So far, the design space of possible Subgraph …

Invariance and equivariance to the rotation group have been widely discussed in the 3D
deep learning community for pointclouds. Yet most proposed methods either use complex …

To date, various 3D scene understanding tasks still lack practical and generalizable pre-
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …

Symmetries and equivariance are fundamental to the generalization of neural networks on
domains such as images, graphs, and point clouds. Existing work has primarily focused on a …

Message-passing neural networks (MPNNs) are the leading architecture for deep learning
on graph-structured data, in large part due to their simplicity and scalability. Unfortunately, it …

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman
algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a …

Despite the great promise of quantum machine learning models, there are several
challenges one must overcome before unlocking their full potential. For instance, models …