{"id":"https://openalex.org/W3126303684","doi":"https://doi.org/10.1145/3449639.3459370","title":"A systematic comparison study on hyperparameter optimisation of graph neural networks for molecular property prediction","display_name":"A systematic comparison study on hyperparameter optimisation of graph neural networks for molecular property prediction","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3126303684","doi":"https://doi.org/10.1145/3449639.3459370","mag":"3126303684"},"language":"en","primary_location":{"id":"doi:10.1145/3449639.3459370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3449639.3459370","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3449639.3459370","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3449639.3459370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yingfang Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yingfang Yuan","raw_affiliation_strings":["Heriot-Watt University, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Heriot-Watt University, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenjun Wang","raw_affiliation_strings":["Heriot-Watt University, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Heriot-Watt University, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Pang","raw_affiliation_strings":["Heriot-Watt University, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Heriot-Watt University, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I32062511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32062511"],"apc_list":null,"apc_paid":null,"fwci":6.2053,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.97730956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5098000168800354,"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":0.5098000168800354,"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":0.18539999425411224,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.13269999623298645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.9193000197410583},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5554999709129333},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5023000240325928},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.49970000982284546}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9193000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.49970000982284546},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C126661757","wikidata":"https://www.wikidata.org/wiki/Q4925641","display_name":"Random search","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.27639999985694885}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3449639.3459370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3449639.3459370","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3449639.3459370","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.04283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04283","pdf_url":"https://arxiv.org/pdf/2102.04283","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3449639.3459370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3449639.3459370","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3449639.3459370","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6483399613","display_name":null,"funder_award_id":"EP/R020957/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6941632622","display_name":"New Industrial Systems: Manufacturing Immortality","funder_award_id":"EP/R020957/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126303684.pdf","grobid_xml":"https://content.openalex.org/works/W3126303684.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1579744901","https://openalex.org/W1964471150","https://openalex.org/W2151238122","https://openalex.org/W2171857942","https://openalex.org/W2269544137","https://openalex.org/W2290847742","https://openalex.org/W2907492528","https://openalex.org/W2949676527","https://openalex.org/W2962876364","https://openalex.org/W2998993395","https://openalex.org/W3012361514","https://openalex.org/W3041085747","https://openalex.org/W3045164669","https://openalex.org/W3084673918"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"have":[4,70,165],"been":[5,72],"proposed":[6],"for":[7,100,106,151],"a":[8,33,92,123],"wide":[9],"range":[10],"of":[11,23,76,95,142,149],"graph-related":[12],"learning":[13,63,191],"tasks.":[14],"In":[15,87,155],"particular,":[16],"in":[17,60,74,83,133,169,193],"recent":[18],"years,":[19],"an":[20],"increasing":[21],"number":[22],"GNN":[24,185],"systems":[25],"were":[26],"applied":[27,187],"to":[28,37,41,138,188],"predict":[29],"molecular":[30,51,85,152,173,189],"properties.":[31],"However,":[32],"direct":[34],"impediment":[35],"is":[36,120],"select":[38],"appropriate":[39],"hyperparameters":[40],"achieve":[42],"satisfactory":[43],"performance":[44],"with":[45,115],"lower":[46],"computational":[47],"cost.":[48],"Meanwhile,":[49],"many":[50,57],"datasets":[52,59,82],"are":[53,127],"far":[54],"smaller":[55],"than":[56],"other":[58],"typical":[61],"deep":[62],"applications.":[64],"Most":[65],"hyperparameter":[66],"optimization":[67],"(HPO)":[68],"methods":[69],"not":[71],"explored":[73],"terms":[75],"their":[77,166],"efficiencies":[78],"on":[79,130,147,184],"such":[80],"small":[81],"the":[84,140],"domain.":[86],"this":[88],"paper,":[89],"we":[90,112,158,176],"conducted":[91],"theoretical":[93],"analysis":[94],"common":[96],"and":[97,103,109,111,145,163,195],"specific":[98,172],"features":[99],"two":[101],"state-of-the-art":[102],"popular":[104],"algorithms":[105],"HPO:":[107],"TPE":[108],"CMA-ES,":[110],"compared":[113],"them":[114],"random":[116],"search":[117],"(RS),":[118],"which":[119],"used":[121],"as":[122,186],"baseline.":[124],"Experimental":[125],"studies":[126],"carried":[128],"out":[129],"several":[131],"benchmarks":[132],"MoleculeNet,":[134],"from":[135],"different":[136,171],"perspectives":[137],"investigate":[139],"impact":[141],"RS,":[143,161],"TPE,":[144,162],"CMA-ES":[146,164],"HPO":[148],"GNNs":[150],"property":[153],"prediction.":[154],"our":[156,178],"experiments,":[157],"concluded":[159],"that":[160],"individual":[167],"advantages":[168],"tackling":[170],"problems.":[174],"Finally,":[175],"believe":[177],"work":[179],"will":[180],"motivate":[181],"further":[182],"research":[183],"machine":[190],"problems":[192],"chemistry":[194],"materials":[196],"sciences.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-02-15T00:00:00"}