{"id":"https://openalex.org/W3189953745","doi":"https://doi.org/10.24963/ijcai.2021/444","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","display_name":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3189953745","doi":"https://doi.org/10.24963/ijcai.2021/444","mag":"3189953745"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/444","pdf_url":"https://www.ijcai.org/proceedings/2021/0444.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0444.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040860593","display_name":"Mengqi Xue","orcid":"https://orcid.org/0000-0003-4936-4887"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Xue","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047371218","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-3671-6521"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015574447","display_name":"Xinchao Wang","orcid":"https://orcid.org/0000-0003-0057-1404"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xinchao Wang","raw_affiliation_strings":["National University of Singapore","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383084","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0002-7769-216X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042307193","display_name":"Xingen Wang","orcid":"https://orcid.org/0000-0003-0507-5020"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xingen Wang","raw_affiliation_strings":["National University of Singapore","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4198,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69411691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3228","last_page":"3234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9987999796867371,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831835746765137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6586049199104309},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5956763029098511},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5920411348342896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5901496410369873},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5755956768989563},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5573886632919312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5338925719261169},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5328282117843628},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5198274254798889},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.496188223361969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4683985412120819},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.462595134973526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10098356008529663},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06355035305023193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831835746765137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6586049199104309},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5956763029098511},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5920411348342896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5901496410369873},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5755956768989563},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5573886632919312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5338925719261169},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5328282117843628},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5198274254798889},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.496188223361969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4683985412120819},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.462595134973526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10098356008529663},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06355035305023193},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/444","pdf_url":"https://www.ijcai.org/proceedings/2021/0444.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/444","pdf_url":"https://www.ijcai.org/proceedings/2021/0444.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326707","display_name":"State Grid Corporation of China","ror":"https://ror.org/05twwhs70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3189953745.pdf","grobid_xml":"https://content.openalex.org/works/W3189953745.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W2133564696","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2561238782","https://openalex.org/W2562979205","https://openalex.org/W2754084392","https://openalex.org/W2803023299","https://openalex.org/W2896457183","https://openalex.org/W2951527505","https://openalex.org/W2955192706","https://openalex.org/W2963122961","https://openalex.org/W2963125010","https://openalex.org/W2963140444","https://openalex.org/W2963370235","https://openalex.org/W2963534679","https://openalex.org/W2963777504","https://openalex.org/W2964111476","https://openalex.org/W2964137095","https://openalex.org/W2970726176","https://openalex.org/W2981413347","https://openalex.org/W2982242214","https://openalex.org/W2995607862","https://openalex.org/W3004809259","https://openalex.org/W3034756453","https://openalex.org/W3034795332","https://openalex.org/W3093410149","https://openalex.org/W3108643758","https://openalex.org/W3110791298","https://openalex.org/W3113223504","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1],"(KD)":[2],"has":[3,30,108],"recently":[4],"emerged":[5],"as":[6,46,78,127],"an":[7],"efficacious":[8],"scheme":[9],"for":[10],"learning":[11],"compact":[12],"deep":[13],"neural":[14],"networks":[15],"(DNNs).":[16],"Despite":[17],"the":[18,22,26,52,56,60,99],"promising":[19],"results":[20,147],"achieved,":[21],"rationale":[23],"that":[24,95,132,149],"interprets":[25],"behavior":[27],"of":[28,62,68],"KD":[29,96,173],"yet":[31],"remained":[32],"largely":[33],"understudied.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,93,120],"introduce":[39,122],"a":[40,65,73,79,87,123,151],"novel":[41],"task-oriented":[42],"attention":[43,129],"model,":[44],"termed":[45],"KDExplainer,":[47,92],"to":[48,91,111,140],"shed":[49],"light":[50],"on":[51,117],"working":[53],"mechanism":[54],"underlying":[55],"vanilla":[57,188],"KD.":[58,145,189],"At":[59],"heart":[61],"KDExplainer":[63],"is":[64,76,184,192],"Hierarchical":[66],"Mixture":[67],"Experts":[69],"(HME),":[70],"in":[71,106,178],"which":[72],"multi-class":[74],"classification":[75],"reformulated":[77],"multi-task":[80],"binary":[81],"one.":[82],"Through":[83],"distilling":[84],"knowledge":[85,100],"from":[86],"free-form":[88],"pre-trained":[89],"DNN":[90],"observe":[94],"implicitly":[97],"modulates":[98],"conflicts":[101],"between":[102],"different":[103,166],"subtasks,":[104],"and":[105],"reality":[107],"much":[109],"more":[110],"offer":[112],"than":[113],"label":[114],"smoothing.":[115],"Based":[116],"such":[118],"findings,":[119],"further":[121],"portable":[124],"tool,":[125],"dubbed":[126],"virtual":[128],"module":[130],"(VAM),":[131],"can":[133],"be":[134],"seamlessly":[135],"integrated":[136],"with":[137,150,158,171],"various":[138],"DNNs":[139],"enhance":[141],"their":[142,162],"performance":[143],"under":[144],"Experimental":[146],"demonstrate":[148],"negligible":[152],"additional":[153],"cost,":[154],"student":[155],"models":[156],"equipped":[157],"VAM":[159,175],"consistently":[160],"outperform":[161],"non-VAM":[163],"counterparts":[164],"across":[165],"benchmarks.":[167],"Furthermore,":[168],"when":[169],"combined":[170],"other":[172],"methods,":[174],"remains":[176],"competent":[177],"promoting":[179],"results,":[180],"even":[181],"though":[182],"it":[183],"only":[185],"motivated":[186],"by":[187],"The":[190],"code":[191],"available":[193],"at":[194],"https://":[195],"github.com/zju-vipa/KDExplainer.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}