Pith. sign in

REVIEW 1 cited by

Equivariant Matrix Function Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.10434 v2 pith:BTMRPHXH submitted 2023-10-16 stat.ML cond-mat.mtrl-scics.LGphysics.chem-ph

classification stat.MLcond-mat.mtrl-scics.LGphysics.chem-ph
keywords networksneuralinteractionsmatrixnon-localarchitecturecapturechallenges
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Neural Networks (GNNs), especially message-passing neural networks (MPNNs), have emerged as powerful architectures for learning on graphs in diverse applications. However, MPNNs face challenges when modeling non-local interactions in graphs such as large conjugated molecules, and social networks due to oversmoothing and oversquashing. Although Spectral GNNs and traditional neural networks such as recurrent neural networks and transformers mitigate these challenges, they often lack generalizability, or fail to capture detailed structural relationships or symmetries in the data. To address these concerns, we introduce Matrix Function Neural Networks (MFNs), a novel architecture that parameterizes non-local interactions through analytic matrix equivariant functions. Employing resolvent expansions offers a straightforward implementation and the potential for linear scaling with system size. The MFN architecture achieves stateof-the-art performance in standard graph benchmarks, such as the ZINC and TU datasets, and is able to capture intricate non-local interactions in quantum systems, paving the way to new state-of-the-art force fields.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning the Electronic Hamiltonian of Large Atomic Structures

    cond-mat.mtrl-sci 2025-01 conditional novelty 6.0 of 10

    A local equivariant GNN with virtual-node graph slicing predicts DFT Hamiltonians of 1,000-3,000 atom amorphous materials, with a 0.53% norm-relative eigenvalue spectrum error and 2.17-2.58 meV element-wise error on h...

Pith tools