arXiv AI August 3, 2026 By Yonatan Sverdlov, Nadav Dym

On the Expressive Power of Sparse Geometric MPNNs

arXiv:2407. 02025v5 Announce Type: replace-cross Abstract: 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 3-dimensional positions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv Machine Learning

Aug 4

Differentiable Lifting for Topological Neural Networks

arXiv:2608. 01160v1 Announce Type: new Abstract: Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.

By Jorge Luiz Franco, Gabriel Duarte, Alexander Nikitin, Moacir Ponti, Diego Mesquita, Amauri H. Souza

benchmarks

arXiv AI

Sep 1

Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs

arXiv:2608.28853v1 Announce Type: cross Abstract: Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how...

By Alessio Borgi, Mario Severino, Fabrizio Silvestri, Pietro Li\`o

arXiv AI

Aug 25

Which Algorithms Can Graph Neural Networks Learn?

arXiv:2602.13106v2 Announce Type: replace-cross Abstract: In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a li...

By Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris

efficiency

arXiv Machine Learning

Sep 2

Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials

arXiv:2609.00528v1 Announce Type: new Abstract: We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy su...

By Pingbing Ming, Han Wang

arXiv Machine Learning

Jun 30

Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks

arXiv:2603. 14846v3 Announce Type: replace Abstract: We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph Neural Network (MP-GNN) model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is super-exponential (in number of vertices).

By Eran Rosenbluth

arXiv Machine Learning

Jun 25

Ramanujan Graph Rewiring with Non Negative Resistance Curvature

arXiv:2606. 21333v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning on graph-structured data by iteratively propagating and aggregating information across edges.

By Hugo Attali, Rachid El Jouhri

rag benchmarks

One email a morning, machine-written

Related stories

Differentiable Lifting for Topological Neural Networks

Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs

Which Algorithms Can Graph Neural Networks Learn?

Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials

Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks

Ramanujan Graph Rewiring with Non Negative Resistance Curvature