{"id":"https://openalex.org/W4393152562","doi":"https://doi.org/10.1609/aaai.v38i21.30436","title":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract)","display_name":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers (Student Abstract)","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393152562","doi":"https://doi.org/10.1609/aaai.v38i21.30436"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i21.30436","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30436","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30436/32520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30436/32520","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101581324","display_name":"Danilo Dordevic","orcid":"https://orcid.org/0009-0004-9002-8521"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Danilo Dordevic","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093299981","display_name":"Vukasin Bozic","orcid":"https://orcid.org/0009-0007-7484-4483"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vukasin Bozic","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093299982","display_name":"Joseph Thommes","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Joseph Thommes","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054153175","display_name":"Daniele Coppola","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniele Coppola","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020425968","display_name":"Sidak Pal Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sidak Pal Singh","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101581324"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.4742,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91272345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"38","issue":"21","first_page":"23477","last_page":"23479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.6998999714851379,"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/T10320","display_name":"Neural Networks and Applications","score":0.6998999714851379,"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/transformer","display_name":"Transformer","score":0.7130056023597717},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5150777697563171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44994276762008667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3071051239967346},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.29321807622909546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27778589725494385},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.052753448486328125}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7130056023597717},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5150777697563171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44994276762008667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3071051239967346},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.29321807622909546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27778589725494385},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.052753448486328125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v38i21.30436","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30436","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30436/32520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i21.30436","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30436","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30436/32520","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393152562.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2131241448","https://openalex.org/W2134797427","https://openalex.org/W3005389111","https://openalex.org/W4297797729","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6774062504","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0,101],"work":[1],"presents":[2],"an":[3],"analysis":[4],"of":[5,8,18,37,66,74,98,109],"the":[6,16,19,23,38,42,50,60,64,72,75,96,107],"effectiveness":[7],"using":[9,49],"standard":[10],"shallow":[11,110],"feed-forward":[12,46,111],"networks":[13,112],"to":[14,70,122],"mimic":[15],"behavior":[17],"attention":[20,39,115],"mechanism":[21,40],"in":[22,41,113],"original":[24,51,76],"Transformer":[25,43],"model,":[26],"a":[27],"state-of-the-art":[28],"architecture":[29],"for":[30,126],"sequence-to-sequence":[31,127],"tasks.":[32,128],"We":[33],"substitute":[34],"key":[35],"elements":[36],"with":[44,84],"simple":[45],"networks,":[47],"trained":[48],"components":[52],"via":[53],"knowledge":[54],"distillation.":[55],"Our":[56],"experiments,":[57],"conducted":[58],"on":[59,106],"IWSLT2017":[61],"dataset,":[62],"reveal":[63],"capacity":[65],"these":[67],"\u201dattentionless":[68],"Transformers\u201d":[69],"rival":[71],"performance":[73],"architecture.":[77],"Through":[78],"rigorous":[79],"ablation":[80],"studies,":[81],"and":[82,89],"experimenting":[83],"various":[85],"replacement":[86],"network":[87],"types":[88],"sizes,":[90],"we":[91],"offer":[92],"insights":[93],"that":[94],"support":[95],"viability":[97],"our":[99],"approach.":[100],"not":[102],"only":[103],"sheds":[104],"light":[105],"adaptability":[108],"emulating":[114],"mechanisms":[116],"but":[117],"also":[118],"underscores":[119],"their":[120],"potential":[121],"streamline":[123],"complex":[124],"architectures":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2025-12-31T23:11:33.660297","created_date":"2025-10-10T00:00:00"}