{"id":"https://openalex.org/W4401090713","doi":"https://doi.org/10.1145/3682075","title":"Multimodal Pre-training for Sequential Recommendation via Contrastive Learning","display_name":"Multimodal Pre-training for Sequential Recommendation via Contrastive Learning","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401090713","doi":"https://doi.org/10.1145/3682075"},"language":"en","primary_location":{"id":"doi:10.1145/3682075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3682075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3682075","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3682075","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014948519","display_name":"Lingzi Zhang","orcid":"https://orcid.org/0000-0001-5319-875X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lingzi Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5319-875X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060375325","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0003-0948-8033"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0948-8033","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049109106","display_name":"Zhiwei Zeng","orcid":"https://orcid.org/0000-0002-7787-5644"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiwei Zeng","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7787-5644","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101789458","display_name":"Zhiqi Shen","orcid":"https://orcid.org/0000-0001-7626-7295"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiqi Shen","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7626-7295","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":18.6148,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.99192062,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.97079998254776,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.97079998254776,"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/computer-science","display_name":"Computer science","score":0.7567817568778992},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6427226662635803},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6006997227668762},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5956184267997742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5860005021095276},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49440836906433105},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4822733998298645},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4722710847854614},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4396820366382599},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43346381187438965},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.411857545375824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39913421869277954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.397843599319458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567817568778992},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6427226662635803},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6006997227668762},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5956184267997742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860005021095276},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49440836906433105},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4822733998298645},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4722710847854614},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4396820366382599},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43346381187438965},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.411857545375824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39913421869277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.397843599319458},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3682075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3682075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3682075","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3682075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3682075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3682075","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401090713.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2069065514","https://openalex.org/W2531563875","https://openalex.org/W2595233870","https://openalex.org/W2604738573","https://openalex.org/W2900841426","https://openalex.org/W2914865568","https://openalex.org/W2914911817","https://openalex.org/W2966715458","https://openalex.org/W2970971581","https://openalex.org/W3065542300","https://openalex.org/W3100260481","https://openalex.org/W3119313768","https://openalex.org/W3152972811","https://openalex.org/W3178835722","https://openalex.org/W3192113933","https://openalex.org/W3199736415","https://openalex.org/W3201053014","https://openalex.org/W3201519611","https://openalex.org/W3205778609","https://openalex.org/W3208227120","https://openalex.org/W4205091644","https://openalex.org/W4206633947","https://openalex.org/W4213069590","https://openalex.org/W4213245422","https://openalex.org/W4225109328","https://openalex.org/W4226377323","https://openalex.org/W4239019441","https://openalex.org/W4246698901","https://openalex.org/W4290877962","https://openalex.org/W4295312788","https://openalex.org/W4309185982","https://openalex.org/W4322718576","https://openalex.org/W4367047350","https://openalex.org/W4384648324","https://openalex.org/W4386065413","https://openalex.org/W4386071687","https://openalex.org/W4387841511","https://openalex.org/W4396843986"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Sequential":[0,110],"recommendation":[1,31,38,234,249],"systems":[2],"often":[3,41],"suffer":[4],"from":[5],"data":[6,71,74],"sparsity,":[7],"leading":[8],"to":[9,23,43,118,170,186,195],"suboptimal":[10],"performance.":[11],"While":[12],"multimodal":[13,36,70,84,101,148,173,230],"content,":[14],"such":[15],"as":[16,128,130,238],"images":[17],"and":[18,46,54,72,98,139,162,191,202,220,242],"text,":[19],"has":[20],"been":[21],"utilized":[22],"mitigate":[24],"this":[25,80],"issue,":[26],"its":[27],"integration":[28],"within":[29],"sequential":[30,37,90,233],"frameworks":[32],"remains":[33],"challenging.":[34],"Current":[35],"models":[39],"are":[40],"unable":[42],"effectively":[44],"explore":[45,83],"capture":[47,119,196],"correlations":[48,61],"among":[49,62,122,133],"behavior":[50],"sequences":[51,125,136],"of":[52,89,95,100,126,137,143,175,228],"users":[53,138],"items":[55],"across":[56],"different":[57,123,134,188],"modalities,":[58],"either":[59],"neglecting":[60],"sequence":[63,73,183],"representations":[64],"or":[65],"inadequately":[66],"capturing":[67],"associations":[68],"between":[69],"in":[75,86,217,232],"their":[76],"representations.":[77],"To":[78],"address":[79],"problem,":[81],"we":[82],"pre-training":[85,164,231],"the":[87,93,120,131,200,226,244,248],"context":[88],"recommendation,":[91],"with":[92],"aim":[94],"enhancing":[96],"fusion":[97],"utilization":[99],"information.":[102],"We":[103,223],"propose":[104],"a":[105,152,181],"novel":[106],"Multimodal":[107,155],"Pre-training":[108],"for":[109,247],"Recommendation":[111],"(MP4SR)":[112],"framework,":[113],"which":[114],"utilizes":[115],"contrastive":[116,193],"losses":[117],"correlation":[121,132],"modality":[124,135,189,197],"users,":[127],"well":[129],"items.":[140],"MP4SR":[141,213],"consists":[142],"three":[144],"key":[145],"components:":[146],"(1)":[147],"feature":[149],"extraction;":[150],"(2)":[151],"backbone":[153],"network,":[154],"Mixup":[156],"Sequence":[157],"Encoder":[158],"(M":[159],"2":[160,178],"SE);":[161],"(3)":[163],"tasks.":[165],"After":[166],"utilizing":[167],"pre-trained":[168],"encoders":[169],"generate":[171],"initial":[172],"features":[174],"items,":[176],"M":[177],"SE":[179],"adopts":[180],"complementary":[182],"mixup":[184],"strategy":[185],"fuse":[187],"sequences,":[190],"leverages":[192],"learning":[194],"interactions":[198],"at":[199],"sequence-to-sequence":[201],"sequence-to-item":[203],"levels.":[204],"Extensive":[205],"experiments":[206],"on":[207],"four":[208],"real-world":[209],"datasets":[210],"demonstrate":[211],"that":[212],"outperforms":[214],"state-of-the-art":[215],"approaches":[216],"both":[218],"normal":[219],"cold-start":[221],"settings.":[222],"further":[224],"highlight":[225],"efficacy":[227],"incorporating":[229],"representation":[235],"learning,":[236],"serving":[237],"an":[239],"effective":[240],"regularizer":[241],"optimizing":[243],"parameter":[245],"space":[246],"task.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}