{"id":"https://openalex.org/W4386081317","doi":"https://doi.org/10.1145/3604915.3608831","title":"Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation","display_name":"Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4386081317","doi":"https://doi.org/10.1145/3604915.3608831"},"language":"en","primary_location":{"id":"doi:10.1145/3604915.3608831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.10347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000544794","display_name":"Vivian Lai","orcid":"https://orcid.org/0000-0003-3165-6136"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vivian Lai","raw_affiliation_strings":["Visa Research, USA"],"raw_orcid":"https://orcid.org/0000-0003-3165-6136","affiliations":[{"raw_affiliation_string":"Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004341287","display_name":"Huiyuan Chen","orcid":"https://orcid.org/0000-0002-6360-558X"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyuan Chen","raw_affiliation_strings":["Research, Visa Research, USA"],"raw_orcid":"https://orcid.org/0000-0002-6360-558X","affiliations":[{"raw_affiliation_string":"Research, Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011045620","display_name":"Chin\u2010Chia Michael Yeh","orcid":"https://orcid.org/0000-0002-9807-2963"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Chia Michael Yeh","raw_affiliation_strings":["Visa Research, Visa Research, USA"],"raw_orcid":"https://orcid.org/0000-0002-9807-2963","affiliations":[{"raw_affiliation_string":"Visa Research, Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101552818","display_name":"Minghua Xu","orcid":"https://orcid.org/0009-0002-7746-2468"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghua Xu","raw_affiliation_strings":["Visa Research, USA"],"raw_orcid":"https://orcid.org/0009-0002-7746-2468","affiliations":[{"raw_affiliation_string":"Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980648","display_name":"Yiwei Cai","orcid":"https://orcid.org/0009-0002-3532-4323"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwei Cai","raw_affiliation_strings":["Visa Research, USA"],"raw_orcid":"https://orcid.org/0009-0002-3532-4323","affiliations":[{"raw_affiliation_string":"Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075211218","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0003-3020-9828"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Visa Research, USA"],"raw_orcid":"https://orcid.org/0000-0003-3020-9828","affiliations":[{"raw_affiliation_string":"Visa Research, USA","institution_ids":["https://openalex.org/I4210148469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000544794"],"corresponding_institution_ids":["https://openalex.org/I4210148469"],"apc_list":null,"apc_paid":null,"fwci":2.2421,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90301336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"797"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9771999716758728,"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/initialization","display_name":"Initialization","score":0.7772939205169678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576079368591309},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7193102836608887},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.595741331577301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.575788140296936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5400112867355347},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49738839268684387},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.4778972864151001},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.43504929542541504},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4151148796081543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10799425840377808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08709138631820679}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7772939205169678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576079368591309},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7193102836608887},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.595741331577301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.575788140296936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400112867355347},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49738839268684387},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.4778972864151001},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.43504929542541504},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4151148796081543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10799425840377808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08709138631820679},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3604915.3608831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.10347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.10347","pdf_url":"https://arxiv.org/pdf/2308.10347","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.10347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.10347","pdf_url":"https://arxiv.org/pdf/2308.10347","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386081317.pdf","grobid_xml":"https://content.openalex.org/works/W4386081317.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2054141820","https://openalex.org/W2140310134","https://openalex.org/W2171279286","https://openalex.org/W2622263826","https://openalex.org/W2777662428","https://openalex.org/W2781528640","https://openalex.org/W2783272285","https://openalex.org/W2896457183","https://openalex.org/W2913754224","https://openalex.org/W2937556626","https://openalex.org/W2963367478","https://openalex.org/W2963959597","https://openalex.org/W2984100107","https://openalex.org/W2992043355","https://openalex.org/W2996931760","https://openalex.org/W3005071803","https://openalex.org/W3065542300","https://openalex.org/W3080292238","https://openalex.org/W3080374445","https://openalex.org/W3100260481","https://openalex.org/W3133849783","https://openalex.org/W3156977692","https://openalex.org/W3158237717","https://openalex.org/W3200593175","https://openalex.org/W3200664681","https://openalex.org/W3206127589","https://openalex.org/W4224316819","https://openalex.org/W4224320470","https://openalex.org/W4224940987","https://openalex.org/W4281861579","https://openalex.org/W4282813352","https://openalex.org/W4284670593","https://openalex.org/W4287126759","https://openalex.org/W4287324301","https://openalex.org/W4287343372","https://openalex.org/W4287646898","https://openalex.org/W4287759081","https://openalex.org/W4290943921","https://openalex.org/W4296591843","https://openalex.org/W4297736277","https://openalex.org/W4299286960","https://openalex.org/W4302306577","https://openalex.org/W4312391126","https://openalex.org/W4320233696","https://openalex.org/W4385245566","https://openalex.org/W4385568170","https://openalex.org/W4387344795"],"related_works":["https://openalex.org/W2596692027","https://openalex.org/W2148025067","https://openalex.org/W4295724548","https://openalex.org/W2549189808","https://openalex.org/W2121922170","https://openalex.org/W4210838092","https://openalex.org/W2911467035","https://openalex.org/W2127982566","https://openalex.org/W2153731865","https://openalex.org/W1504381128"],"abstract_inverted_index":{"Transformer":[0],"and":[1,93],"its":[2],"variants":[3],"are":[4],"a":[5,19,37],"powerful":[6],"class":[7],"of":[8,17,36,40,57],"architectures":[9],"for":[10],"sequential":[11,51],"recommendation,":[12],"owing":[13],"to":[14,45,66],"their":[15,24,28],"ability":[16],"capturing":[18],"user\u2019s":[20],"dynamic":[21],"interests":[22],"from":[23,47,73],"past":[25],"interactions.":[26],"Despite":[27],"success,":[29],"Transformer-based":[30],"models":[31],"often":[32],"require":[33],"the":[34,55],"optimization":[35],"large":[38,94],"number":[39],"parameters,":[41],"making":[42],"them":[43],"difficult":[44],"train":[46],"sparse":[48],"data":[49,58,78,91],"in":[50],"recommendation.":[52],"To":[53],"address":[54],"problem":[56],"sparsity,":[59],"previous":[60],"studies":[61],"have":[62],"utilized":[63],"self-supervised":[64],"learning":[65],"enhance":[67],"Transformers,":[68],"such":[69],"as":[70],"pre-training":[71],"embeddings":[72],"item":[74],"attributes":[75],"or":[76],"contrastive":[77],"augmentations.":[79],"However,":[80],"these":[81],"approaches":[82],"encounter":[83],"several":[84],"training":[85],"issues,":[86],"including":[87],"initialization":[88],"sensitivity,":[89],"manual":[90],"augmentations,":[92],"batch-size":[95],"memory":[96],"bottlenecks.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-08-23T00:00:00"}