{"id":"https://openalex.org/W3193949130","doi":"https://doi.org/10.1145/3459637.3482153","title":"Neuron Campaign for Initialization Guided by Information Bottleneck Theory","display_name":"Neuron Campaign for Initialization Guided by Information Bottleneck Theory","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3193949130","doi":"https://doi.org/10.1145/3459637.3482153","mag":"3193949130"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.06530","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065066091","display_name":"Haitao Mao","orcid":"https://orcid.org/0009-0000-8510-3102"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitao Mao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711699","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-5041-0532"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086820941","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-5821-7267"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006300825","display_name":"Shi Han","orcid":"https://orcid.org/0000-0002-0360-6089"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Han","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065066091"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.8399,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78756838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3328","last_page":"3332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9986000061035156,"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":0.9746404886245728},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8086507320404053},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7625183463096619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613185048103333},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7571834921836853},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.7439513802528381},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5894664525985718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5718203186988831},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5508530139923096},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5082408785820007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48133906722068787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15369224548339844},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.11551854014396667}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9746404886245728},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8086507320404053},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7625183463096619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613185048103333},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7571834921836853},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.7439513802528381},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5894664525985718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5718203186988831},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5508530139923096},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5082408785820007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48133906722068787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15369224548339844},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.11551854014396667},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.06530","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06530","pdf_url":"https://arxiv.org/pdf/2108.06530","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":"pmh:oai:arXiv.org:2108.06530","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06530","pdf_url":"https://arxiv.org/pdf/2108.06530","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W2031647436","https://openalex.org/W2125930537","https://openalex.org/W2147768505","https://openalex.org/W2178237821","https://openalex.org/W2194775991","https://openalex.org/W2287334441","https://openalex.org/W2523246573","https://openalex.org/W2557579533","https://openalex.org/W2593634001","https://openalex.org/W2618530766","https://openalex.org/W2803832867","https://openalex.org/W2887997457","https://openalex.org/W2892806280","https://openalex.org/W2896457183","https://openalex.org/W2912719334","https://openalex.org/W2917668703","https://openalex.org/W2951873722","https://openalex.org/W2963192800","https://openalex.org/W2963341956","https://openalex.org/W2964209830","https://openalex.org/W2965265899","https://openalex.org/W3035237680","https://openalex.org/W3035524453","https://openalex.org/W3094193403","https://openalex.org/W3095319910","https://openalex.org/W3126693873","https://openalex.org/W3162752841","https://openalex.org/W4293469690","https://openalex.org/W4297749952","https://openalex.org/W4297798488","https://openalex.org/W4300537377"],"related_works":["https://openalex.org/W2622284819","https://openalex.org/W2999408031","https://openalex.org/W1504394672","https://openalex.org/W3089381707","https://openalex.org/W4367625101","https://openalex.org/W4285254085","https://openalex.org/W3034190530","https://openalex.org/W4385764429","https://openalex.org/W3193949130","https://openalex.org/W2741297526"],"abstract_inverted_index":{"Initialization":[0],"plays":[1],"a":[2,48,81,89,93,97,112],"critical":[3],"role":[4],"in":[5,34],"the":[6,20,57,63],"training":[7,21],"of":[8,59],"deep":[9],"neural":[10,94],"networks":[11],"(DNN).":[12],"Existing":[13],"initialization":[14,30,84,91],"strategies":[15],"mainly":[16],"focus":[17],"on":[18,96,102],"stabilizing":[19],"process":[22],"to":[23,38,52,86,111],"mitigate":[24],"gradient":[25],"vanish/explosion":[26],"problems.":[27],"However,":[28],"these":[29],"methods":[31],"are":[32],"lacking":[33],"consideration":[35],"about":[36,56],"how":[37],"enhance":[39],"generalization":[40,58,114],"ability.":[41],"The":[42,100],"Information":[43],"Bottleneck":[44],"(IB)":[45],"theory":[46],"is":[47],"well-known":[49],"understanding":[50],"framework":[51],"provide":[53],"an":[54],"explanation":[55],"DNN.":[60,76],"Guided":[61],"by":[62,66],"insights":[64],"provided":[65],"IB":[67],"theory,":[68],"we":[69,78],"design":[70,80],"two":[71],"criteria":[72],"for":[73,92],"better":[74,113],"initializing":[75],"And":[77],"further":[79],"neuron":[82],"campaign":[83],"algorithm":[85],"efficiently":[87],"select":[88],"good":[90],"network":[95],"given":[98],"dataset.":[99],"experiments":[101],"MNIST":[103],"dataset":[104],"show":[105],"that":[106],"our":[107],"method":[108],"can":[109],"lead":[110],"performance":[115],"with":[116],"faster":[117],"convergence.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-08-30T00:00:00"}