{"id":"https://openalex.org/W4280500920","doi":"https://doi.org/10.1088/2632-2153/ac99ba","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","display_name":"Chemical transformer compression for accelerating both training and inference of molecular modeling","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4280500920","doi":"https://doi.org/10.1088/2632-2153/ac99ba"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ac99ba","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac99ba","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac99ba/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac99ba/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079058531","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0001-8360-005X"},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Department of Chemistry and Molecular Biology, University of Gothenburg, Kemiv\u00e4gen 10, 412 96 Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Molecular Biology, University of Gothenburg, Kemiv\u00e4gen 10, 412 96 Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057304913","display_name":"Karl B\u00f6rjesson","orcid":"https://orcid.org/0000-0001-8533-201X"},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Karl B\u00f6rjesson","raw_affiliation_strings":["Department of Chemistry and Molecular Biology, University of Gothenburg, Kemiv\u00e4gen 10, 412 96 Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Molecular Biology, University of Gothenburg, Kemiv\u00e4gen 10, 412 96 Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057304913"],"corresponding_institution_ids":["https://openalex.org/I881427289"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":0.075,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29458554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"4","first_page":"045009","last_page":"045009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7690305709838867},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.742409884929657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7022601366043091},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.6615157723426819},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"Applicability domain","score":0.511300802230835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4961174428462982},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4862312376499176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46603816747665405},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15288394689559937},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09341365098953247}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7690305709838867},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.742409884929657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7022601366043091},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.6615157723426819},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.511300802230835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4961174428462982},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4862312376499176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46603816747665405},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15288394689559937},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09341365098953247},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1088/2632-2153/ac99ba","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac99ba","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac99ba/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ac99ba","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac99ba","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac99ba/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4280500920.pdf","grobid_xml":"https://content.openalex.org/works/W4280500920.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1975147762","https://openalex.org/W1975875968","https://openalex.org/W2039749139","https://openalex.org/W2066532920","https://openalex.org/W2136605707","https://openalex.org/W2290847742","https://openalex.org/W2558999090","https://openalex.org/W2578240541","https://openalex.org/W2594183968","https://openalex.org/W2866343820","https://openalex.org/W2883583109","https://openalex.org/W2900694120","https://openalex.org/W2901476322","https://openalex.org/W2924902521","https://openalex.org/W2937307539","https://openalex.org/W2970454332","https://openalex.org/W2973114758","https://openalex.org/W2978017171","https://openalex.org/W2980282514","https://openalex.org/W2992586577","https://openalex.org/W2996428491","https://openalex.org/W3007488165","https://openalex.org/W3008219293","https://openalex.org/W3008374555","https://openalex.org/W3009321976","https://openalex.org/W3012320348","https://openalex.org/W3012519883","https://openalex.org/W3030978062","https://openalex.org/W3034457371","https://openalex.org/W3037029945","https://openalex.org/W3045928028","https://openalex.org/W3093859587","https://openalex.org/W3093934881","https://openalex.org/W3100157108","https://openalex.org/W3100358278","https://openalex.org/W3105966348","https://openalex.org/W3109892317","https://openalex.org/W3157265962","https://openalex.org/W3171707284","https://openalex.org/W3176005660","https://openalex.org/W3178702014","https://openalex.org/W3215689235","https://openalex.org/W4200179152","https://openalex.org/W4221074165","https://openalex.org/W4226159083","https://openalex.org/W4291288469","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6753640285","https://openalex.org/W6760732026","https://openalex.org/W6766978945","https://openalex.org/W6768021236","https://openalex.org/W6768086466","https://openalex.org/W6768817161","https://openalex.org/W6768851824","https://openalex.org/W6773815586","https://openalex.org/W6774009640","https://openalex.org/W6784526300","https://openalex.org/W6786619936","https://openalex.org/W6796905988","https://openalex.org/W6797735627"],"related_works":["https://openalex.org/W2142085049","https://openalex.org/W227407425","https://openalex.org/W3011161038","https://openalex.org/W3117501106","https://openalex.org/W2066657428","https://openalex.org/W2274497585","https://openalex.org/W2562984628","https://openalex.org/W2795113352","https://openalex.org/W4310940448","https://openalex.org/W4280500920"],"abstract_inverted_index":{"Abstract":[0],"Transformer":[1],"models":[2,185],"have":[3,81],"been":[4],"developed":[5],"in":[6,12,41,74,151],"molecular":[7,75],"science":[8],"with":[9,24],"excellent":[10],"performance":[11,85,150],"applications":[13],"including":[14],"quantitative":[15],"structure-activity":[16],"relationship":[17],"(QSAR)":[18],"and":[19,33,52,62,103,127,133,141,153,161,189],"virtual":[20],"screening":[21],"(VS).":[22],"Compared":[23],"other":[25],"types":[26],"of":[27,72,136,139,156,181],"models,":[28],"however,":[29],"they":[30],"are":[31,66,95],"large":[32],"need":[34],"voluminous":[35],"data":[36],"for":[37,49,125,186],"training,":[38],"which":[39],"results":[40],"a":[42,106,112,131,176],"high":[43],"hardware":[44],"requirement":[45],"to":[46,68,88,130,178],"abridge":[47],"time":[48],"both":[50],"training":[51,126],"inference":[53],"processes.":[54],"In":[55],"this":[56],"work,":[57],"cross-layer":[58],"parameter":[59,97],"sharing":[60],"(CLPS),":[61],"knowledge":[63,163],"distillation":[64],"(KD)":[65],"used":[67],"reduce":[69],"the":[70,89,137,145,171,179],"sizes":[71],"transformers":[73],"science.":[76],"Both":[77],"methods":[78],"not":[79],"only":[80],"competitive":[82],"QSAR":[83,152],"predictive":[84],"as":[86],"compared":[87],"original":[90],"BERT":[91],"model,":[92,118],"but":[93],"also":[94],"more":[96],"efficient.":[98],"Furthermore,":[99],"by":[100],"integrating":[101],"CLPS":[102],"KD":[104],"into":[105],"two-state":[107],"chemical":[108,116],"network,":[109],"we":[110,168],"introduce":[111],"new":[113],"deep":[114],"lite":[115],"transformer":[117,184],"DeLiCaTe.":[119],"DeLiCaTe":[120],"accomplishes":[121],"4\u00d7":[122],"faster":[123],"rate":[124],"inference,":[128],"due":[129],"10-":[132],"3-times":[134],"reduction":[135],"number":[138],"parameters":[140],"layers,":[142],"respectively.":[143],"Meanwhile,":[144],"integrated":[146],"model":[147,172],"achieves":[148],"comparable":[149],"VS,":[154],"because":[155],"capturing":[157],"general-domain":[158],"(basic":[159],"structure)":[160],"task-specific":[162],"(specific":[164],"property":[165],"prediction).":[166],"Moreover,":[167],"anticipate":[169],"that":[170],"compression":[173],"strategy":[174],"provides":[175],"pathway":[177],"creation":[180],"effective":[182],"generative":[183],"organic":[187],"drugs":[188],"material":[190],"design.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}