{"id":"https://openalex.org/W3037412002","doi":"https://doi.org/10.1145/3394486.3403165","title":"Retrospective Loss: Looking Back to Improve Training of Deep Neural Networks","display_name":"Retrospective Loss: Looking Back to Improve Training of Deep Neural Networks","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3037412002","doi":"https://doi.org/10.1145/3394486.3403165","mag":"3037412002"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.13593","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046611496","display_name":"Surgan Jandial","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Surgan Jandial","raw_affiliation_strings":["Indian Institute of Technology Hyderabad, Hyderabad, India","Indian Institute of Technology \u2013 Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Indian Institute of Technology \u2013 Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057677536","display_name":"Ayush Chopra","orcid":"https://orcid.org/0000-0002-4070-4139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayush Chopra","raw_affiliation_strings":["Adobe, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112660758","display_name":"Mausoom Sarkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mausoom Sarkar","raw_affiliation_strings":["Adobe, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124832","display_name":"Piyush Gupta","orcid":"https://orcid.org/0000-0002-5141-2406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piyush Gupta","raw_affiliation_strings":["Adobe, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024546524","display_name":"Balaji Krishnamurthy","orcid":"https://orcid.org/0000-0002-0366-2427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaji Krishnamurthy","raw_affiliation_strings":["Adobe, Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe, Noida, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038020125","display_name":"Vineeth N Balasubramanian","orcid":"https://orcid.org/0000-0003-2656-0375"},"institutions":[{"id":"https://openalex.org/I1321014770","display_name":"Association for Computing Machinery","ror":"https://ror.org/03wsadn68","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321014770"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Vineeth Balasubramanian","raw_affiliation_strings":["Indian Institute of Technology Hyderabad, Hyderabad, India","Association for Computing Machinery"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Association for Computing Machinery","institution_ids":["https://openalex.org/I1321014770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06860237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1123","last_page":"1131"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.7562175989151001},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7207682132720947},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6790606379508972},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.660964846611023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6328192353248596},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6297723650932312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.621596097946167},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5602200031280518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5350633263587952},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4765641987323761},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20230156183242798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0788971483707428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562175989151001},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7207682132720947},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6790606379508972},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.660964846611023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6328192353248596},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6297723650932312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.621596097946167},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5602200031280518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5350633263587952},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4765641987323761},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20230156183242798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0788971483707428},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3394486.3403165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.13593","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13593","pdf_url":"https://arxiv.org/pdf/2006.13593","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3037412002","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.13593.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:raiith.iith.ac.in:8610","is_oa":false,"landing_page_url":"http://raiith.iith.ac.in/8610/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"doi:10.48550/arxiv.2006.13593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.13593","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.13593","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13593","pdf_url":"https://arxiv.org/pdf/2006.13593","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037412002.pdf","grobid_xml":"https://content.openalex.org/works/W3037412002.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W1532499126","https://openalex.org/W1771410628","https://openalex.org/W1797268635","https://openalex.org/W2092206588","https://openalex.org/W2096733369","https://openalex.org/W2107438106","https://openalex.org/W2117539524","https://openalex.org/W2138621090","https://openalex.org/W2145339207","https://openalex.org/W2146334809","https://openalex.org/W2153959628","https://openalex.org/W2163605009","https://openalex.org/W2173520492","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2310919327","https://openalex.org/W2335728318","https://openalex.org/W2432004435","https://openalex.org/W2601450892","https://openalex.org/W2736601468","https://openalex.org/W2750384547","https://openalex.org/W2765407302","https://openalex.org/W2914057340","https://openalex.org/W2918342466","https://openalex.org/W2950776302","https://openalex.org/W2962696654","https://openalex.org/W2962835968","https://openalex.org/W2963399829","https://openalex.org/W2963487351","https://openalex.org/W2963741406","https://openalex.org/W2963775347","https://openalex.org/W2964015378","https://openalex.org/W2964300796","https://openalex.org/W2971353280","https://openalex.org/W2998508940","https://openalex.org/W3099206234","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3080441097","https://openalex.org/W3200659000","https://openalex.org/W3205859423","https://openalex.org/W2922317475","https://openalex.org/W2901809754","https://openalex.org/W2900836049","https://openalex.org/W2946813660","https://openalex.org/W3126266540","https://openalex.org/W2952943736","https://openalex.org/W2903047678","https://openalex.org/W2535731875","https://openalex.org/W2407712415","https://openalex.org/W2551883569","https://openalex.org/W3130227562","https://openalex.org/W2807985048","https://openalex.org/W3199325788","https://openalex.org/W2911502716","https://openalex.org/W2295050354","https://openalex.org/W3211976353","https://openalex.org/W3009270141"],"abstract_inverted_index":{"Deep":[0],"neural":[1,30],"networks":[2],"(DNNs)":[3],"are":[4],"powerful":[5],"learning":[6],"machines":[7],"that":[8,109],"have":[9],"enabled":[10],"breakthroughs":[11],"in":[12,39,114],"several":[13],"domains.":[14],"In":[15],"this":[16],"work,":[17],"we":[18,85],"introduce":[19],"a":[20,77,82],"new":[21],"retrospective":[22,47],"loss":[23,112],"to":[24,92,107],"improve":[25],"the":[26,35,46,51,55,59,64,73,87,110],"training":[27,61,79],"of":[28,96],"deep":[29],"network":[31],"models":[32],"by":[33],"utilizing":[34],"prior":[36],"experience":[37],"available":[38],"past":[40],"model":[41],"states":[42],"during":[43],"training.":[44],"Minimizing":[45],"loss,":[48,53],"along":[49],"with":[50],"task-specific":[52],"pushes":[54],"parameter":[56,66,74],"state":[57,67,75],"at":[58,76],"current":[60],"step":[62],"towards":[63],"optimal":[65],"while":[68],"pulling":[69],"it":[70],"away":[71],"from":[72],"previous":[78],"step.":[80],"Although":[81],"simple":[83],"idea,":[84],"analyze":[86],"method":[88],"as":[89,91],"well":[90],"conduct":[93],"comprehensive":[94],"sets":[95],"experiments":[97],"across":[98,117],"domains":[99],"-":[100,106],"images,":[101],"speech,":[102],"text,":[103],"and":[104,121],"graphs":[105],"show":[108],"proposed":[111],"results":[113],"improved":[115],"performance":[116],"input":[118],"domains,":[119],"tasks,":[120],"architectures.":[122]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}