{"id":"https://openalex.org/W4412877025","doi":"https://doi.org/10.1145/3711896.3737266","title":"TayFCS: Towards Light Feature Combination Selection for Deep Recommender Systems","display_name":"TayFCS: Towards Light Feature Combination Selection for Deep Recommender Systems","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877025","doi":"https://doi.org/10.1145/3711896.3737266"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737266","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737266","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737266","source":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737266","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058613427","display_name":"Xianquan Wang","orcid":"https://orcid.org/0009-0003-9744-220X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianquan Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-9744-220X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040755010","display_name":"Zhaocheng Du","orcid":"https://orcid.org/0000-0002-1811-129X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaocheng Du","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1811-129X","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5666-8320","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001967239","display_name":"Chuhan Wu","orcid":"https://orcid.org/0000-0001-5730-8792"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuhan Wu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5730-8792","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032579783","display_name":"Qinglin Jia","orcid":"https://orcid.org/0000-0002-3583-6719"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Jia","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-6719","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021124418","display_name":"Zhenhua Dong","orcid":"https://orcid.org/0000-0002-2231-4663"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Dong","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2231-4663","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5007","last_page":"5017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":1.0,"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":1.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.982200026512146,"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/recommender-system","display_name":"Recommender system","score":0.8628873825073242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7776389122009277},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6865371465682983},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5788325071334839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676485300064087},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.564988911151886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34406712651252747}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8628873825073242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776389122009277},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6865371465682983},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5788325071334839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676485300064087},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.564988911151886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34406712651252747},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.1145/3711896.3737266","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737266","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737266","source":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.03895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03895","pdf_url":"https://arxiv.org/pdf/2507.03895","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:10.1145/3711896.3737266","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737266","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737266","source":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877025.pdf","grobid_xml":"https://content.openalex.org/works/W4412877025.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2025357764","https://openalex.org/W2475334473","https://openalex.org/W2512971201","https://openalex.org/W2548570154","https://openalex.org/W2604662567","https://openalex.org/W2768044475","https://openalex.org/W2793768763","https://openalex.org/W2963832024","https://openalex.org/W2964182926","https://openalex.org/W2966501701","https://openalex.org/W3012731857","https://openalex.org/W3024538121","https://openalex.org/W3098862241","https://openalex.org/W3104030692","https://openalex.org/W3108823960","https://openalex.org/W3114904768","https://openalex.org/W3132743969","https://openalex.org/W3155874371","https://openalex.org/W3173713405","https://openalex.org/W3192708477","https://openalex.org/W3208543775","https://openalex.org/W4224227049","https://openalex.org/W4224251646","https://openalex.org/W4282576620","https://openalex.org/W4290874950","https://openalex.org/W4310631727","https://openalex.org/W4367310145","https://openalex.org/W4384828482","https://openalex.org/W4385568204","https://openalex.org/W4385568319","https://openalex.org/W4386557465","https://openalex.org/W4387846269","https://openalex.org/W4387846842","https://openalex.org/W4387847689","https://openalex.org/W4400914197","https://openalex.org/W4409367461"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4288390103","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Feature":[0],"interaction":[1],"modeling":[2],"is":[3,14,39],"crucial":[4],"for":[5,72,122],"deep":[6],"recommendation":[7,172],"models.":[8],"A":[9],"common":[10],"and":[11,49,145,182,218,232],"effective":[12],"approach":[13],"to":[15,20,41,46,65,82,151],"construct":[16],"explicit":[17],"feature":[18,44,54,74,91,104,135,143,180,197],"combinations":[19,33,45,92,181,198],"enhance":[21],"model":[22,111],"performance.":[23,112],"However,":[24],"in":[25,86],"practice,":[26],"only":[27,149],"a":[28,78,102,170],"small":[29],"fraction":[30],"of":[31,131,196,220],"these":[32,70],"are":[34,62],"truly":[35],"informative.":[36],"Thus":[37],"it":[38],"essential":[40],"select":[42],"useful":[43],"reduce":[47,176],"noise":[48],"manage":[50],"memory":[51],"consumption.":[52],"While":[53],"selection":[55,76,106],"methods":[56,71],"have":[57],"been":[58],"extensively":[59],"studied,":[60],"they":[61],"typically":[63],"limited":[64],"selecting":[66],"individual":[67],"features.":[68],"Extending":[69],"high-order":[73],"combination":[75,105],"presents":[77],"significant":[79],"challenge":[80],"due":[81],"the":[83,116,127,193,204,216],"exponential":[84],"growth":[85],"time":[87],"complexity":[88],"when":[89],"evaluating":[90,132],"one":[93,165],"by":[94,138],"one.":[95],"In":[96],"this":[97,147],"paper,":[98],"we":[99,114,185],"propose":[100,115],"TayFCS,":[101],"lightweight":[103],"method":[107],"that":[108,191],"significantly":[109],"improves":[110],"Specifically,":[113],"Taylor":[117,124],"Expansion":[118],"Scorer":[119],"(TayScorer)":[120],"module":[121],"field-wise":[123],"expansion":[125],"on":[126,155,169,203,210],"base":[128],"model.":[129,173],"Instead":[130],"all":[133],"potential":[134],"combinations'":[136],"importance":[137,206],"repeatedly":[139],"running":[140],"experiments":[141],"with":[142,164],"adding":[144],"removal,":[146],"scorer":[148],"needs":[150],"approximate":[152],"them":[153],"based":[154,168,202],"their":[156,183,200],"sub-components'":[157],"gradients.":[158],"They":[159],"can":[160],"be":[161],"simply":[162],"computed":[163],"backward":[166],"pass":[167],"trained":[171],"To":[174],"further":[175],"information":[177,194],"redundancy":[178],"between":[179],"sub-components,":[184],"introduce":[186],"Logistic":[187],"Regression":[188],"Elimination":[189],"(LRE)":[190],"estimates":[192],"gain":[195],"over":[199],"sub-components":[201],"above":[205],"scores.":[207],"Experimental":[208],"results":[209,227],"three":[211],"benchmark":[212],"datasets":[213],"validate":[214],"both":[215],"effectiveness":[217],"efficiency":[219],"our":[221],"approach.":[222],"Furthermore,":[223],"online":[224],"A/B":[225],"test":[226],"demonstrate":[228],"its":[229],"practical":[230],"applicability":[231],"commercial":[233],"value.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}