{"id":"https://openalex.org/W7162803064","doi":"https://doi.org/10.48550/arxiv.2605.30195","title":"What drives performance in molecular MPNNs? An operator-level factorial benchmark","display_name":"What drives performance in molecular MPNNs? An operator-level factorial benchmark","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162803064","doi":"https://doi.org/10.48550/arxiv.2605.30195"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30195","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30195","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.2605.30195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136464942","display_name":"panyu Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Panyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137375348","display_name":"Shuizhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shuizhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137326664","display_name":"Yiheng Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137391449","display_name":"Yuyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062012847","display_name":"Runhai Ouyang","orcid":"https://orcid.org/0000-0001-9020-0484"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Runhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137381803","display_name":"Wei Xie","orcid":"https://orcid.org/0000-0003-4508-3041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Wei","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.3528999984264374,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.3528999984264374,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.243599995970726,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.22759999334812164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.682200014591217},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5322999954223633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5314000248908997},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4691999852657318},{"id":"https://openalex.org/keywords/design-of-experiments","display_name":"Design of experiments","score":0.46309998631477356},{"id":"https://openalex.org/keywords/factorial-experiment","display_name":"Factorial experiment","score":0.4205999970436096},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.40880000591278076},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.40149998664855957},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5507000088691711},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C34559072","wikidata":"https://www.wikidata.org/wiki/Q2334061","display_name":"Design of experiments","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C169222746","wikidata":"https://www.wikidata.org/wiki/Q4116558","display_name":"Factorial experiment","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C16469947","wikidata":"https://www.wikidata.org/wiki/Q2400745","display_name":"Fractional factorial design","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30195","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30195","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.2605.30195","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30195","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Message-passing":[0],"neural":[1,166],"networks":[2],"(MPNNs)":[3],"are":[4,56,182],"widely":[5],"used":[6],"for":[7,93,105,110,122,154,201],"molecular":[8,37,164,202],"property":[9],"prediction,":[10],"but":[11],"their":[12],"deployment":[13],"as":[14],"monolithic":[15,212],"architectures":[16,213],"makes":[17],"it":[18],"difficult":[19],"to":[20,162],"identify":[21],"how":[22,221],"specific":[23],"message-passing":[24,226],"operators":[25],"affect":[26],"performance.":[27],"We":[28],"present":[29],"an":[30],"operator-level":[31],"factorial":[32],"benchmark":[33,177],"that":[34,135],"decomposes":[35],"2D":[36],"MPNNs":[38,203],"into":[39,129,214],"the":[40,114,130,225],"three":[41],"families":[42],"of":[43,175,188,218],"message-seed":[44],"initialization,":[45],"node-edge":[46,98,190],"fusion,":[47],"and":[48,67,96,113,144,156,192,220],"node":[49],"update":[50,85,115,193],"operators.":[51,194],"The":[52],"resulting":[53],"84":[54],"configurations":[55,151],"benchmarked":[57],"on":[58,173],"ten":[59,176],"MoleculeNet":[60],"datasets":[61],"under":[62],"a":[63,101,209,215],"shared":[64],"experimental":[65],"setup":[66],"statistical":[68],"analysis":[69],"protocol.":[70],"Across":[71],"this":[72],"controlled":[73],"design,":[74],"performance":[75,160],"variation":[76],"is":[77],"associated":[78],"primarily":[79],"with":[80,107],"message":[81],"construction":[82],"rather":[83],"than":[84,147],"complexity.":[86],"Message-seed":[87],"initialization":[88],"shows":[89,100,117],"significant":[90,102],"family-level":[91,103],"effects":[92],"both":[94],"regression":[95,106,157],"classification,":[97],"fusion":[99,191],"effect":[104,121],"descriptive":[108],"advantages":[109],"concatenation-based":[111,136],"mixing,":[112],"family":[116],"no":[118],"statistically":[119],"supported":[120],"either":[123],"endpoint":[124],"family.":[125],"A":[126],"representation":[127],"probe":[128],"Quinethazone":[131],"molecule":[132],"further":[133],"demonstrates":[134],"mixing":[137],"can":[138],"better":[139],"differentiate":[140],"chemically":[141],"distinct":[142],"heteroatoms":[143],"withstand":[145],"oversmoothing":[146],"Hadamard":[148],"gating.":[149],"Representative":[150],"selected":[152],"separately":[153],"classification":[155],"recover":[158],"competitive":[159],"relative":[161],"established":[163],"graph":[165],"network":[167],"(GNN)":[168],"baselines,":[169],"ranking":[170],"numerically":[171],"best":[172],"eight":[174],"datasets.":[178],"These":[179],"empirical":[180,198],"results":[181],"interpreted":[183],"through":[184],"concise":[185],"mechanistic":[186],"analyses":[187],"representative":[189],"Our":[195],"findings":[196],"provide":[197],"design":[199,207],"heuristics":[200],"by":[204],"turning":[205],"model":[206],"from":[208],"search":[210],"over":[211],"targeted":[216],"assessment":[217],"where":[219],"chemical":[222],"information":[223],"enters":[224],"pipeline.":[227]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}