{"id":"https://openalex.org/W4416078509","doi":"https://doi.org/10.1145/3746252.3761076","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","display_name":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078509","doi":"https://doi.org/10.1145/3746252.3761076"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761076","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761076","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["Data 61, CSIRO, Eveleigh, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Eveleigh, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358930","display_name":"Siyu Wang","orcid":"https://orcid.org/0009-0008-8726-5277"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siyu Wang","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8726-5277","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["Data 61, CSIRO, Eveleigh, Australia and The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Eveleigh, Australia and The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6157,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86432145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"322","last_page":"331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.917900025844574,"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":0.917900025844574,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.013299999758601189,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.011699999682605267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8109999895095825},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6651999950408936},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.5537999868392944},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5353999733924866},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.4514999985694885},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.43459999561309814},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.428600013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123000264167786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8109999895095825},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5698000192642212},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5537999868392944},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4973999857902527},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761076","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761076","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416078509.pdf","grobid_xml":"https://content.openalex.org/works/W4416078509.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2020631728","https://openalex.org/W2562337727","https://openalex.org/W2787933113","https://openalex.org/W2799544270","https://openalex.org/W2963440040","https://openalex.org/W2963654596","https://openalex.org/W2964108915","https://openalex.org/W3017289192","https://openalex.org/W3159587374","https://openalex.org/W3208231292","https://openalex.org/W4292419518","https://openalex.org/W4292423901","https://openalex.org/W4318159260","https://openalex.org/W4324312897","https://openalex.org/W4384891727","https://openalex.org/W4387846486","https://openalex.org/W4390872297","https://openalex.org/W4393147800","https://openalex.org/W4400528915","https://openalex.org/W4407838716","https://openalex.org/W4409657161"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning-based":[1],"recommender":[2],"systems":[3,19],"(RL4RS)":[4],"have":[5],"gained":[6],"attention":[7],"for":[8,76],"their":[9,35],"ability":[10,166],"to":[11,13,46,58,90,105,120,132,167],"adapt":[12],"dynamic":[14],"user":[15,61,93,170],"preferences.":[16,171],"However,":[17],"these":[18,48,70],"face":[20],"challenges,":[21],"particularly":[22],"in":[23,64,159,190],"offline":[24,39,110,156],"settings,":[25],"where":[26],"data":[27,55],"inefficiency":[28],"and":[29,56,113,141,158,195],"reliance":[30],"on":[31,153],"pre-collected":[32],"trajectories":[33],"limit":[34],"broader":[36],"applicability.":[37,197],"While":[38],"reinforcement":[40,88],"learning":[41,89],"methods":[42],"leverage":[43],"extensive":[44,151],"datasets":[45,157],"address":[47],"issues,":[49],"they":[50],"often":[51],"struggle":[52],"with":[53,87],"noisy":[54],"fail":[57],"capture":[59],"long-term":[60,169],"preferences,":[62],"resulting":[63],"suboptimal":[65,123],"recommendation":[66,136],"policies.":[67],"To":[68],"overcome":[69],"limitations,":[71],"we":[72,126,173],"propose":[73],"Diffusion-enhanced":[74],"Actor-Critic":[75],"Offline":[77],"RL4RS":[78],"(DAC4Rec),":[79],"a":[80,115],"novel":[81],"framework":[82],"that":[83,175],"integrates":[84],"diffusion":[85,103,178],"processes":[86],"model":[91],"complex":[92],"preferences":[94],"more":[95,139],"effectively.":[96],"DAC4Rec":[97,149],"leverages":[98],"the":[99,107,146,176],"denoising":[100],"capabilities":[101],"of":[102,109,148],"models":[104],"enhance":[106],"robustness":[108],"RL":[111,188],"algorithms":[112,189],"incorporates":[114],"Q-value-guided":[116],"policy":[117,179],"optimization":[118],"strategy":[119,131],"better":[121],"handle":[122],"trajectories.":[124],"Additionally,":[125],"introduce":[127],"an":[128,160],"energy-based":[129],"sampling":[130],"reduce":[133],"randomness":[134],"during":[135],"generation,":[137],"ensuring":[138],"targeted":[140],"reliable":[142],"outcomes.":[143],"We":[144],"validate":[145],"effectiveness":[147],"through":[150],"experiments":[152],"six":[154],"real-world":[155],"online":[161],"simulation":[162],"environment,":[163],"demonstrating":[164],"its":[165,193],"optimize":[168],"Furthermore,":[172],"show":[174],"proposed":[177],"can":[180],"be":[181],"seamlessly":[182],"integrated":[183],"into":[184],"other":[185],"commonly":[186],"used":[187],"RL4RS,":[191],"highlighting":[192],"versatility":[194],"wide":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-11-10T00:00:00"}