{"id":"https://openalex.org/W7170082175","doi":"https://doi.org/10.48550/arxiv.2607.19083","title":"GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks","display_name":"GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks","publication_year":2026,"publication_date":"2026-07-21","ids":{"openalex":"https://openalex.org/W7170082175","doi":"https://doi.org/10.48550/arxiv.2607.19083"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.19083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.19083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.19083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085446880","display_name":"Daniele Angioletti","orcid":"https://orcid.org/0009-0003-0890-5082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angioletti, Daniele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024148071","display_name":"Marco Nobile","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobile, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026034661","display_name":"Vittorio Limongelli","orcid":"https://orcid.org/0000-0002-4861-1199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Limongelli, Vittorio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8776000142097473,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8776000142097473,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.08089999854564667,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.6643999814987183},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44449999928474426},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41119998693466187},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40459999442100525},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40049999952316284},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3400000035762787},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3370000123977661},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.33570000529289246},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.6643999814987183},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.19083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.19083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.19083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.19083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6466856002807617,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Equivariant":[0],"graph":[1],"neural":[2],"networks":[3],"provide":[4],"a":[5,32,80,130,148,155,186,195],"powerful":[6],"modeling":[7,239],"language":[8],"for":[9],"three-dimensional":[10],"scientific":[11],"data,":[12],"but":[13,126],"their":[14],"reuse":[15],"is":[16,118],"often":[17],"limited":[18],"by":[19,200],"implementations":[20],"tied":[21],"to":[22,48,79,120,127,183,236],"specific":[23],"tasks,":[24],"outputs,":[25],"and":[26,41,52,59,72,112,133,176,215,228,231,243],"training":[27,42,60,73,134],"regimes.":[28],"We":[29,86,151,190],"present":[30],"GEqTrain,":[31],"configuration-driven":[33],"framework":[34],"that":[35,129,205],"separates":[36],"dataset":[37],"semantics,":[38],"model":[39,56],"composition,":[40],"objectives.":[43],"Raw":[44],"data":[45],"are":[46,62],"mapped":[47],"typed":[49],"node-,":[50],"edge-,":[51],"graph-level":[53],"fields,":[54],"while":[55],"stacks,":[57],"losses,":[58],"workflows":[61],"assembled":[63],"declaratively":[64],"through":[65,84],"Hydra":[66],"configurations.":[67],"A":[68],"shared":[69,131],"equivariant":[70,113,160,166,188,238],"backbone":[71],"infrastructure":[74,135],"can":[75,136,211],"therefore":[76],"be":[77,212],"retargeted":[78],"new":[81],"task":[82],"primarily":[83],"configuration.":[85],"demonstrate":[87],"this":[88,192],"flexibility":[89],"on":[90,159,194],"three":[91],"different":[92,142],"problems":[93],"handled":[94],"within":[95,185],"one":[96],"software":[97,222],"stack:":[98],"coarse-grained-to-atomistic":[99],"backmapping":[100],"of":[101,105,147,224],"biomolecular":[102],"systems,":[103,125],"prediction":[104],"NMR":[106],"chemical":[107],"shifts":[108],"in":[109],"molecular":[110],"solids,":[111],"generative":[114,156],"modeling.":[115],"Our":[116],"aim":[117],"not":[119],"surpass":[121],"individually":[122],"optimized":[123],"task-specific":[124],"show":[128],"representation":[132],"achieve":[137],"competitive":[138],"accuracy":[139],"across":[140],"qualitatively":[141],"tasks":[143],"at":[144],"the":[145,221],"cost":[146],"configuration":[149],"change.":[150],"further":[152],"introduce":[153],"GEqDiff,":[154],"extension":[157],"based":[158],"flow":[161],"matching.":[162],"GEqDiff":[163],"treats":[164],"user-defined":[165],"fields":[167,179,206],"as":[168],"first-class":[169],"generation":[170],"targets,":[171],"jointly":[172,214],"transporting":[173],"Cartesian":[174],"positions":[175],"non-scalar":[177],"node":[178],"spanning":[180],"representations":[181],"up":[182],"l=3":[184],"single":[187],"flow.":[189],"validate":[191],"capability":[193],"controlled":[196],"synthetic":[197],"benchmark":[198],"inspired":[199],"protein":[201],"secondary-structure":[202],"motifs,":[203],"showing":[204],"with":[207,216],"heterogeneous":[208],"transformation":[209],"properties":[210],"reconstructed":[213],"high":[217],"fidelity.":[218],"By":[219],"reducing":[220],"overhead":[223],"moving":[225],"between":[226],"predictive":[227],"generative,":[229],"scalar":[230],"tensorial":[232],"settings,":[233],"GEqTrain":[234],"aims":[235],"make":[237],"more":[240],"reproducible,":[241],"extensible,":[242],"reusable.":[244]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-23T00:00:00"}