Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384206875> ?p ?o ?g. }
- W4384206875 abstract "Density-based representations of atomic environments that are invariant under Euclidean symmetries have become a widely used tool in the machine learning of interatomic potentials, broader data-driven atomistic modeling, and the visualization and analysis of material datasets. The standard mechanism used to incorporate chemical element information is to create separate densities for each element and form tensor products between them. This leads to a steep scaling in the size of the representation as the number of elements increases. Graph neural networks, which do not explicitly use density representations, escape this scaling by mapping the chemical element information into a fixed dimensional space in a learnable way. By exploiting symmetry, we recast this approach as tensor factorization of the standard neighbour-density-based descriptors and, using a new notation, identify connections to existing compression algorithms. In doing so, we form compact tensor-reduced representation of the local atomic environment whose size does not depend on the number of chemical elements, is systematically convergable, and therefore remains applicable to a wide range of data analysis and regression tasks." @default.
- W4384206875 created "2023-07-14" @default.
- W4384206875 creator A5034025853 @default.
- W4384206875 creator A5035097475 @default.
- W4384206875 creator A5040590113 @default.
- W4384206875 creator A5041825525 @default.
- W4384206875 creator A5044182171 @default.
- W4384206875 creator A5061841111 @default.
- W4384206875 creator A5074124442 @default.
- W4384206875 date "2023-07-13" @default.
- W4384206875 modified "2023-09-26" @default.
- W4384206875 title "Tensor-Reduced Atomic Density Representations" @default.
- W4384206875 cites W1501987263 @default.
- W4384206875 cites W1596134677 @default.
- W4384206875 cites W2025444507 @default.
- W4384206875 cites W2029413789 @default.
- W4384206875 cites W2039748980 @default.
- W4384206875 cites W2083415705 @default.
- W4384206875 cites W2600893352 @default.
- W4384206875 cites W26088913 @default.
- W4384206875 cites W2650911154 @default.
- W4384206875 cites W2776192919 @default.
- W4384206875 cites W2910857709 @default.
- W4384206875 cites W2911997094 @default.
- W4384206875 cites W2942913009 @default.
- W4384206875 cites W2943241318 @default.
- W4384206875 cites W2963339823 @default.
- W4384206875 cites W2991989817 @default.
- W4384206875 cites W3041909131 @default.
- W4384206875 cites W3043300003 @default.
- W4384206875 cites W3044111935 @default.
- W4384206875 cites W3088965305 @default.
- W4384206875 cites W3096619549 @default.
- W4384206875 cites W3098544579 @default.
- W4384206875 cites W3102033477 @default.
- W4384206875 cites W3112410551 @default.
- W4384206875 cites W3119697748 @default.
- W4384206875 cites W3157478677 @default.
- W4384206875 cites W3164680271 @default.
- W4384206875 cites W3185227028 @default.
- W4384206875 cites W3189164715 @default.
- W4384206875 cites W3196804715 @default.
- W4384206875 cites W3198396303 @default.
- W4384206875 cites W3208707586 @default.
- W4384206875 cites W3209893332 @default.
- W4384206875 cites W3210084966 @default.
- W4384206875 cites W4205793477 @default.
- W4384206875 cites W4207013141 @default.
- W4384206875 cites W4225405705 @default.
- W4384206875 cites W4282041110 @default.
- W4384206875 cites W4282053982 @default.
- W4384206875 cites W4290805632 @default.
- W4384206875 cites W4290989292 @default.
- W4384206875 cites W4308944249 @default.
- W4384206875 doi "https://doi.org/10.1103/physrevlett.131.028001" @default.
- W4384206875 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37505943" @default.
- W4384206875 hasPublicationYear "2023" @default.
- W4384206875 type Work @default.
- W4384206875 citedByCount "1" @default.
- W4384206875 countsByYear W43842068752023 @default.
- W4384206875 crossrefType "journal-article" @default.
- W4384206875 hasAuthorship W4384206875A5034025853 @default.
- W4384206875 hasAuthorship W4384206875A5035097475 @default.
- W4384206875 hasAuthorship W4384206875A5040590113 @default.
- W4384206875 hasAuthorship W4384206875A5041825525 @default.
- W4384206875 hasAuthorship W4384206875A5044182171 @default.
- W4384206875 hasAuthorship W4384206875A5061841111 @default.
- W4384206875 hasAuthorship W4384206875A5074124442 @default.
- W4384206875 hasBestOaLocation W43842068751 @default.
- W4384206875 hasConcept C121332964 @default.
- W4384206875 hasConcept C154945302 @default.
- W4384206875 hasConcept C155281189 @default.
- W4384206875 hasConcept C17744445 @default.
- W4384206875 hasConcept C190470478 @default.
- W4384206875 hasConcept C199539241 @default.
- W4384206875 hasConcept C202444582 @default.
- W4384206875 hasConcept C2524010 @default.
- W4384206875 hasConcept C2776359362 @default.
- W4384206875 hasConcept C33923547 @default.
- W4384206875 hasConcept C36464697 @default.
- W4384206875 hasConcept C41008148 @default.
- W4384206875 hasConcept C62520636 @default.
- W4384206875 hasConcept C80444323 @default.
- W4384206875 hasConcept C94625758 @default.
- W4384206875 hasConcept C96469262 @default.
- W4384206875 hasConcept C99844830 @default.
- W4384206875 hasConceptScore W4384206875C121332964 @default.
- W4384206875 hasConceptScore W4384206875C154945302 @default.
- W4384206875 hasConceptScore W4384206875C155281189 @default.
- W4384206875 hasConceptScore W4384206875C17744445 @default.
- W4384206875 hasConceptScore W4384206875C190470478 @default.
- W4384206875 hasConceptScore W4384206875C199539241 @default.
- W4384206875 hasConceptScore W4384206875C202444582 @default.
- W4384206875 hasConceptScore W4384206875C2524010 @default.
- W4384206875 hasConceptScore W4384206875C2776359362 @default.
- W4384206875 hasConceptScore W4384206875C33923547 @default.
- W4384206875 hasConceptScore W4384206875C36464697 @default.
- W4384206875 hasConceptScore W4384206875C41008148 @default.
- W4384206875 hasConceptScore W4384206875C62520636 @default.
- W4384206875 hasConceptScore W4384206875C80444323 @default.