Injective multiset functions have a key role in the theoretical study of machine learning on
multisets and graphs. Yet, there remains a gap between the provably injective multiset …

Recent advances in computational modelling of atomic systems, spanning molecules,
proteins, and materials, represent them as geometric graphs with atoms embedded as …

Invariant models, one important class of geometric deep learning models, are capable of
generating meaningful geometric representations by leveraging informative geometric …

Intrinsically disordered proteins have dynamic structures through which they play key
biological roles. The elucidation of their conformational ensembles is a challenging problem …

We revisit the classical result of Morris et al.~(AAAI'19) that message-passing graphs neural
networks (MPNNs) are equal in their distinguishing power to the Weisfeiler--Leman (WL) …

Recent advancements in molecular generative models have demonstrated substantial
potential in accelerating scientific discovery, particularly in drug design. However, these …

Graph neural networks (GNNs) have achieved remarkable success in a variety of machine
learning tasks over graph data. Existing GNNs usually rely on message passing, ie …

The $ k $-Weifeiler-Leman ($ k $-WL) graph isomorphism test hierarchy is a common
method for assessing the expressive power of graph neural networks (GNNs). Recently, the …

The capability to learn latent representations plays a key role in the effectiveness of recent
machine learning methods. An active frontier in representation learning is understanding …

Motivated by applications in chemistry and other sciences, we study the expressive power of
message-passing neural networks for geometric graphs, whose node features correspond to …