{"id":"https://openalex.org/W4416942395","doi":"https://doi.org/10.1145/3770854.3780231","title":"Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation","display_name":"Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W4416942395","doi":"https://doi.org/10.1145/3770854.3780231"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3780231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780231","pdf_url":null,"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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008836594","display_name":"Tao Zhe","orcid":"https://orcid.org/0000-0003-4942-9775"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zhe","raw_affiliation_strings":["University of Kansas, Lawrence, Kansas, USA"],"raw_orcid":"https://orcid.org/0000-0003-4942-9775","affiliations":[{"raw_affiliation_string":"University of Kansas, Lawrence, Kansas, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103016808","display_name":"Huazhen Fang","orcid":"https://orcid.org/0000-0003-0147-4817"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huazhen Fang","raw_affiliation_strings":["Michigan State University, East Lansing, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0003-4759-1672","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, Michigan, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100786547","display_name":"Kunpeng Liu","orcid":"https://orcid.org/0000-0002-6053-5977"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Liu","raw_affiliation_strings":["Clemson University, Clemson, South Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0002-6053-5977","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, South Carolina, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006753786","display_name":"Qian Lou","orcid":"https://orcid.org/0000-0001-5462-2567"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Lou","raw_affiliation_strings":["University of Central Florida, Orlando, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0001-5462-2567","affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073744069","display_name":"Tamzidul Hoque","orcid":"https://orcid.org/0000-0002-6845-0361"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamzidul Hoque","raw_affiliation_strings":["University of Kansas, Lawrence, Kansas, USA"],"raw_orcid":"https://orcid.org/0000-0002-6845-0361","affiliations":[{"raw_affiliation_string":"University of Kansas, Lawrence, Kansas, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101737969","display_name":"Dongjie Wang","orcid":"https://orcid.org/0000-0003-3948-0059"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongjie Wang","raw_affiliation_strings":["University of Kansas, Lawrence, Kansas, USA"],"raw_orcid":"https://orcid.org/0000-0003-3948-0059","affiliations":[{"raw_affiliation_string":"University of Kansas, Lawrence, Kansas, USA","institution_ids":["https://openalex.org/I146416000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03086259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2010","last_page":"2019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2029000073671341,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2029000073671341,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.15600000321865082,"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":0.0754999965429306,"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/interpretability","display_name":"Interpretability","score":0.7768999934196472},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7440999746322632},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6905999779701233},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6258000135421753},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5476999878883362},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4740999937057495},{"id":"https://openalex.org/keywords/feature-model","display_name":"Feature model","score":0.459199994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842000126838684},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7768999934196472},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488999724388123},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5547000169754028},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.459199994802475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4341000020503998},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3770854.3780231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780231","pdf_url":null,"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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.21934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.21934","pdf_url":"https://arxiv.org/pdf/2511.21934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2511.21934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21934","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780231","pdf_url":null,"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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Feature":[0],"transformation":[1,21,44,90,183,196,262],"enhances":[2],"downstream":[3],"task":[4],"performance":[5],"by":[6],"generating":[7],"informative":[8],"features":[9,158,214],"through":[10,73],"mathematical":[11],"feature":[12,20,36,43,86,118,141,162,182,203,209,216,231],"crossing.":[13,163,217],"Despite":[14],"the":[15,89,97,101,181,188,200,242,249,253,271],"advancements":[16],"in":[17,116,257],"deep":[18,29],"learning,":[19],"remains":[22],"essential,":[23],"particularly":[24],"for":[25,104,161,215],"structured":[26],"data,":[27],"where":[28],"models":[30],"often":[31,50],"struggle":[32],"to":[33,58,69,136,155,190,211,245,269],"capture":[34],"complex":[35],"interactions":[37],"effectively.":[38],"Prior":[39],"literature":[40],"on":[41,52,228,287],"automated":[42],"has":[45],"achieved":[46],"notable":[47],"success":[48],"but":[49],"relies":[51],"heuristics":[53],"or":[54],"exhaustive":[55],"searches,":[56],"leading":[57],"inefficient":[59],"and":[60,95,110,121,139,159,194,223,247,260,275,282],"time-consuming":[61],"processes.":[62],"Recent":[63],"works":[64],"employ":[65],"reinforcement":[66],"learning":[67,102,250],"(RL)":[68],"enhance":[70,165,248],"traditional":[71],"approaches":[72],"a":[74,130,172,237],"more":[75,192,258],"effective":[76,195,224],"trial-and-error":[77],"way.":[78],"However,":[79],"two":[80,151],"key":[81],"limitations":[82],"remain:":[83],"1)":[84],"Dynamic":[85],"expansion":[87],"during":[88,180,241],"process,":[91],"which":[92,114],"introduces":[93],"instability":[94],"increases":[96],"time":[98],"complexity":[99],"of":[100,252,277],"procedure":[103],"RL":[105,134,254],"agents;":[106],"2)":[107],"Insufficient":[108],"cooperation":[109],"communication":[111,166],"between":[112],"agents,":[113,148,169,255],"results":[115],"suboptimal":[117],"crossing":[119],"operations":[120,160],"degraded":[122],"model":[123],"performance.":[124],"To":[125,164,198],"address":[126],"them,":[127],"we":[128,170,205,235,265],"propose":[129],"novel":[131],"heterogeneous":[132,147],"multi-agent":[133],"framework":[135,144],"enable":[137],"cooperative":[138],"scalable":[140,221],"transformation.":[142],"The":[143],"comprises":[145],"three":[146],"grouped":[149],"into":[150],"types,":[152],"each":[153],"designed":[154],"select":[156,212],"essential":[157],"among":[167],"these":[168],"implement":[171],"shared":[173],"critic":[174],"mechanism":[175],"that":[176],"facilitates":[177,220],"information":[178],"exchange":[179],"process.":[184],"This":[185,218],"collaboration":[186],"enables":[187],"agents":[189,210],"learn":[191],"intelligent":[193],"policies.":[197,263],"handle":[199],"dynamically":[201],"expanding":[202],"space,":[204],"tailor":[206],"multi-head":[207],"attention-based":[208],"suitable":[213],"design":[219],"decision-making":[222],"candidate":[225],"selection":[226],"based":[227],"comprehensive":[229],"global":[230],"space":[232],"information.":[233],"Additionally,":[234],"introduce":[236],"state":[238],"encoding":[239],"technique":[240],"optimization":[243],"process":[244],"stabilize":[246],"dynamics":[251],"resulting":[256],"robust":[259],"reliable":[261],"Finally,":[264],"conduct":[266],"extensive":[267],"experiments":[268],"validate":[270],"effectiveness,":[272],"efficiency,":[273],"robustness,":[274],"interpretability":[276],"our":[278],"model.":[279],"Our":[280],"code":[281],"dataset":[283],"are":[284],"publicly":[285],"available":[286],"GitHub.":[288]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-12-03T00:00:00"}