{"id":"https://openalex.org/W7160261118","doi":"https://doi.org/10.1145/3779211.3793182","title":"ColdNet: Neural Causal Inference Under Extreme Imbalance and Sparsity","display_name":"ColdNet: Neural Causal Inference Under Extreme Imbalance and Sparsity","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7160261118","doi":"https://doi.org/10.1145/3779211.3793182"},"language":null,"primary_location":{"id":"doi:10.1145/3779211.3793182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793182","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779211.3793182","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101461195","display_name":"M. Saifur Rahman","orcid":"https://orcid.org/0000-0003-1297-8842"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmudur Rahman","raw_affiliation_strings":["Amazon, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0007-4734-5734","affiliations":[{"raw_affiliation_string":"Amazon, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114087001","display_name":"S. K. Tewatia","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanskar Tewatia","raw_affiliation_strings":["Amazon, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0003-3602-8200","affiliations":[{"raw_affiliation_string":"Amazon, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135335860","display_name":"Dhruv Garg","orcid":"https://orcid.org/0009-0004-9300-0911"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Garg","raw_affiliation_strings":["Amazon, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0004-9300-0911","affiliations":[{"raw_affiliation_string":"Amazon, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.70966729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.8554999828338623,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.8554999828338623,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03709999844431877,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.029100000858306885,"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/hyperparameter","display_name":"Hyperparameter","score":0.6406999826431274},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.5609999895095825},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5579000115394592},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.555400013923645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49869999289512634},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47870001196861267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6406999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6079000234603882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6064000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C89337504","wikidata":"https://www.wikidata.org/wiki/Q4828276","display_name":"Average treatment effect","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779211.3793182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793182","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779211.3793182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793182","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2116943185","https://openalex.org/W2258533878","https://openalex.org/W2345125502","https://openalex.org/W2624816748","https://openalex.org/W2962727190","https://openalex.org/W2964983698","https://openalex.org/W2998702515","https://openalex.org/W3081149207","https://openalex.org/W3123436326"],"related_works":[],"abstract_inverted_index":{"Individual":[0],"treatment":[1,34,79,114],"effect":[2],"(ITE)":[3],"estimation":[4],"from":[5,36],"observational":[6],"data":[7],"faces":[8],"fundamental":[9],"challenges":[10],"when":[11],"extreme":[12],"class":[13],"imbalance,":[14],"pervasive":[15],"cold-start":[16,52,87,117,133,175],"scenarios,":[17],"and":[18,29,49,98,119,158],"outcome":[19],"sparsity":[20],"co-occur.":[21],"These":[22],"characteristics":[23],"violate":[24],"core":[25],"identifying":[26],"assumptions\u2014positivity,":[27],"unconfoundedness,":[28],"the":[30,103,129,136,145,174],"ability":[31],"to":[32,156,165],"distinguish":[33],"effects":[35],"noise.":[37],"Classical":[38],"econometric":[39],"methods":[40],"like":[41],"Double":[42],"Machine":[43],"Learning":[44],"require":[45],"manual":[46],"feature":[47],"engineering":[48],"cannot":[50],"handle":[51],"cases,":[53,118,134],"while":[54,81],"neural":[55,67],"causal":[56],"models":[57],"degrade":[58],"severely":[59],"under":[60],"these":[61],"conditions.":[62],"We":[63],"present":[64],"ColdNet,":[65],"a":[66,109],"architecture":[68],"that":[69,76,89,101,184,194],"integrates":[70],"three":[71],"innovations:":[72],"outcome-stratified":[73],"ensemble":[74],"learning":[75],"addresses":[77],"heterogeneous":[78],"imbalance":[80],"maintaining":[82],"propensity":[83],"calibration,":[84],"K-Means":[85,137],"cluster-based":[86],"enhancement":[88,138],"transfers":[90],"counterfactual":[91],"(CF)":[92],"predictions":[93],"via":[94],"locality-preserving":[95],"quantile":[96,185],"aggregation,":[97],"sparsity-aware":[99],"preprocessing":[100],"preserves":[102],"informative":[104],"structure":[105],"of":[106,169],"zeros.":[107],"On":[108],"large-scale":[110],"dataset":[111],"with":[112,135],"0.39%":[113],"rate,":[115],"99.25%":[116],"97.6%":[120],"zero":[121],"outcomes,":[122],"ColdNet":[123],"achieves":[124],"28%":[125],"MAE":[126,191],"reduction":[127],"over":[128],"baseline":[130],"DragonNet":[131],"for":[132,173],"contributing":[139],"an":[140],"additional":[141],"19%":[142],"improvement":[143],"beyond":[144],"Neural":[146],"Causal":[147],"Model":[148],"(NCM).":[149],"Median":[150],"error":[151,172],"drops":[152],"90%":[153],"(from":[154,163],"42":[155],"4)":[157],"median":[159],"bias":[160],"reduces":[161],"98%":[162],"40":[164],"1),":[166],"representing":[167],"near-elimination":[168],"systematic":[170],"prediction":[171],"cohort.":[176],"Comprehensive":[177],"hyperparameter":[178,200],"analysis":[179],"across":[180,198],"18":[181],"configurations":[182],"reveals":[183],"aggregation":[186,189],"is":[187,196],"essential\u2014mean":[188],"worsens":[190],"by":[192],"+1.3%\u2014and":[193],"performance":[195],"robust":[197],"reasonable":[199],"ranges.":[201]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}