Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309136508> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4309136508 abstract "Many learning tasks in physics and chemistry involve global spatial symmetries as well as permutational symmetry between particles. The standard approach to such problems is equivariant neural networks, which employ tensor products between various tensors that transform under the spatial group. However, as the number of different tensors and the complexity of relationships between them increases, the bookkeeping associated with ensuring parsimony as well as equivariance quickly becomes nontrivial. In this paper, we propose to use fusion diagrams, a technique widely used in simulating SU($2$)-symmetric quantum many-body problems, to design new equivariant components for use in equivariant neural networks. This yields a diagrammatic approach to constructing new neural network architectures. We show that when applied to particles in a given local neighborhood, the resulting components, which we call fusion blocks, are universal approximators of any continuous equivariant function defined on the neighborhood. As a practical demonstration, we incorporate a fusion block into a pre-existing equivariant architecture (Cormorant) and show that it improves performance on benchmark molecular learning tasks." @default.
- W4309136508 created "2022-11-23" @default.
- W4309136508 creator A5003806118 @default.
- W4309136508 creator A5040698416 @default.
- W4309136508 creator A5045781240 @default.
- W4309136508 creator A5063639736 @default.
- W4309136508 creator A5070853988 @default.
- W4309136508 date "2022-11-14" @default.
- W4309136508 modified "2023-10-14" @default.
- W4309136508 title "Group-Equivariant Neural Networks with Fusion Diagrams" @default.
- W4309136508 doi "https://doi.org/10.48550/arxiv.2211.07482" @default.
- W4309136508 hasPublicationYear "2022" @default.
- W4309136508 type Work @default.
- W4309136508 citedByCount "0" @default.
- W4309136508 crossrefType "posted-content" @default.
- W4309136508 hasAuthorship W4309136508A5003806118 @default.
- W4309136508 hasAuthorship W4309136508A5040698416 @default.
- W4309136508 hasAuthorship W4309136508A5045781240 @default.
- W4309136508 hasAuthorship W4309136508A5063639736 @default.
- W4309136508 hasAuthorship W4309136508A5070853988 @default.
- W4309136508 hasBestOaLocation W43091365081 @default.
- W4309136508 hasConcept C114614502 @default.
- W4309136508 hasConcept C121332964 @default.
- W4309136508 hasConcept C13280743 @default.
- W4309136508 hasConcept C14036430 @default.
- W4309136508 hasConcept C154945302 @default.
- W4309136508 hasConcept C155281189 @default.
- W4309136508 hasConcept C171036898 @default.
- W4309136508 hasConcept C184720557 @default.
- W4309136508 hasConcept C185798385 @default.
- W4309136508 hasConcept C202444582 @default.
- W4309136508 hasConcept C205649164 @default.
- W4309136508 hasConcept C2524010 @default.
- W4309136508 hasConcept C2777210771 @default.
- W4309136508 hasConcept C2779886137 @default.
- W4309136508 hasConcept C2781311116 @default.
- W4309136508 hasConcept C33923547 @default.
- W4309136508 hasConcept C41008148 @default.
- W4309136508 hasConcept C50644808 @default.
- W4309136508 hasConcept C62520636 @default.
- W4309136508 hasConcept C78458016 @default.
- W4309136508 hasConcept C80444323 @default.
- W4309136508 hasConcept C86803240 @default.
- W4309136508 hasConcept C96469262 @default.
- W4309136508 hasConceptScore W4309136508C114614502 @default.
- W4309136508 hasConceptScore W4309136508C121332964 @default.
- W4309136508 hasConceptScore W4309136508C13280743 @default.
- W4309136508 hasConceptScore W4309136508C14036430 @default.
- W4309136508 hasConceptScore W4309136508C154945302 @default.
- W4309136508 hasConceptScore W4309136508C155281189 @default.
- W4309136508 hasConceptScore W4309136508C171036898 @default.
- W4309136508 hasConceptScore W4309136508C184720557 @default.
- W4309136508 hasConceptScore W4309136508C185798385 @default.
- W4309136508 hasConceptScore W4309136508C202444582 @default.
- W4309136508 hasConceptScore W4309136508C205649164 @default.
- W4309136508 hasConceptScore W4309136508C2524010 @default.
- W4309136508 hasConceptScore W4309136508C2777210771 @default.
- W4309136508 hasConceptScore W4309136508C2779886137 @default.
- W4309136508 hasConceptScore W4309136508C2781311116 @default.
- W4309136508 hasConceptScore W4309136508C33923547 @default.
- W4309136508 hasConceptScore W4309136508C41008148 @default.
- W4309136508 hasConceptScore W4309136508C50644808 @default.
- W4309136508 hasConceptScore W4309136508C62520636 @default.
- W4309136508 hasConceptScore W4309136508C78458016 @default.
- W4309136508 hasConceptScore W4309136508C80444323 @default.
- W4309136508 hasConceptScore W4309136508C86803240 @default.
- W4309136508 hasConceptScore W4309136508C96469262 @default.
- W4309136508 hasLocation W43091365081 @default.
- W4309136508 hasLocation W43091365082 @default.
- W4309136508 hasOpenAccess W4309136508 @default.
- W4309136508 hasPrimaryLocation W43091365081 @default.
- W4309136508 hasRelatedWork W1594396050 @default.
- W4309136508 hasRelatedWork W2022205133 @default.
- W4309136508 hasRelatedWork W2069360731 @default.
- W4309136508 hasRelatedWork W2326201543 @default.
- W4309136508 hasRelatedWork W2892947161 @default.
- W4309136508 hasRelatedWork W2947615180 @default.
- W4309136508 hasRelatedWork W2949640665 @default.
- W4309136508 hasRelatedWork W2949947405 @default.
- W4309136508 hasRelatedWork W3099115740 @default.
- W4309136508 hasRelatedWork W4298192601 @default.
- W4309136508 isParatext "false" @default.
- W4309136508 isRetracted "false" @default.
- W4309136508 workType "article" @default.