{"id":"https://openalex.org/W7161996205","doi":"https://doi.org/10.48550/arxiv.2605.20581","title":"TriForces: Augmenting Atomistic GNNs for Transferable Representations","display_name":"TriForces: Augmenting Atomistic GNNs for Transferable Representations","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161996205","doi":"https://doi.org/10.48550/arxiv.2605.20581"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05630317v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05630317","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML 2026 - International Conference on Machine Learning, Jul 2026, Seoul, South Korea. ⟨10.48550/arXiv.2605.20581⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05630317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104435508","display_name":"Ali Ramlaoui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramlaoui, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083981921","display_name":"Alexandre Duval","orcid":"https://orcid.org/0000-0001-9416-3270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duval, Alexandre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136675052","display_name":"Hannah Bull","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bull, Hannah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136722708","display_name":"Victor Schmidt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmidt, Victor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002452272","display_name":"Hugues Talbot","orcid":"https://orcid.org/0000-0002-2179-3498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talbot, Hugues","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136706587","display_name":"Fragkiskos D. Malliaros","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malliaros, Fragkiskos D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136629844","display_name":"Joseph Musielewicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Musielewicz, Joseph","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":0.9977999925613403,"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":0.9977999925613403,"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/T10211","display_name":"Computational Drug Discovery Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10798","display_name":"Crystallography and molecular interactions","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5228000283241272},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.447299987077713},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.38589999079704285},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.375},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3151000142097473},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30169999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017999887466431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5228000283241272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47290000319480896},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.375},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-05630317v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05630317","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML 2026 - International Conference on Machine Learning, Jul 2026, Seoul, South Korea. ⟨10.48550/arXiv.2605.20581⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2605.20581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20581","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":"pmh:oai:HAL:hal-05630317v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05630317","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML 2026 - International Conference on Machine Learning, Jul 2026, Seoul, South Korea. ⟨10.48550/arXiv.2605.20581⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.898819625377655,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1,71],"interatomic":[2],"potentials":[3],"(MLIPs)":[4],"achieve":[5],"excellent":[6],"accuracy":[7],"when":[8],"trained":[9],"on":[10,79],"large":[11],"Density":[12],"Functional":[13],"Theory":[14],"(DFT)":[15],"data.":[16],"To":[17,52],"be":[18,25],"useful":[19],"in":[20,102],"practice,":[21],"they":[22],"must":[23],"often":[24,45],"adapted":[26],"to":[27,72],"target":[28],"chemistries":[29],"using":[30],"small":[31],"and":[32,49,65,81,89,116],"expensive":[33],"task-specific":[34],"datasets.":[35],"However,":[36],"MLIPs":[37],"transfer":[38],"inconsistently":[39],"across":[40,120,128],"domains,":[41],"with":[42,69,132],"representations":[43],"that":[44,62],"loose":[46],"accessible":[47],"composition":[48,64],"structure":[50,66,93],"information.":[51],"address":[53],"this,":[54],"we":[55],"present":[56],"TriForces,":[57],"a":[58],"model-agnostic":[59],"three-stream":[60],"framework":[61],"separates":[63],"information,":[67],"combined":[68],"self-supervised":[70],"preserve":[73],"transferable":[74],"representations.":[75],"TriForces":[76,106,126],"improves":[77,117],"performance":[78],"MatBench":[80],"QM9":[82],"over":[83],"baselines":[84],"without":[85],"needing":[86],"DFT":[87],"labels":[88],"enables":[90],"efficient":[91],"similar":[92],"retrieval":[94],"through":[95],"its":[96],"learned":[97],"latent":[98],"space.":[99],"On":[100],"OMat24,":[101],"limited-data":[103],"training":[104],"regime,":[105],"reduces":[107],"energy":[108],"MAE":[109,119],"by":[110],"57%":[111],"at":[112,134],"20K":[113],"samples":[114],"only":[115],"force":[118],"sample":[121],"sizes.":[122],"We":[123],"release":[124],"pretrained":[125],"variants":[127],"multiple":[129],"MLIP":[130],"architectures":[131],"code":[133],"https://github.com/Ramlaoui/triforces.":[135]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}