{"id":"https://openalex.org/W7155102296","doi":"https://doi.org/10.48550/arxiv.2604.18390","title":"Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus","display_name":"Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155102296","doi":"https://doi.org/10.48550/arxiv.2604.18390"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18390","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.18390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093489205","display_name":"Esteban Rodr\u00edguez-Betancourt","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rodr\u00edguez-Betancourt, Esteban","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124404772","display_name":"Edgar Casasola-Murillo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Casasola-Murillo, Edgar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093489205"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.2599000036716461,"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":0.2599000036716461,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2409999966621399,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.050599999725818634,"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":0.5428000092506409},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.49320000410079956},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46869999170303345},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.4237000048160553},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.3176000118255615},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3068000078201294},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3061999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523000001907349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165000200271606},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5278000235557556},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.4237000048160553},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18390","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.18390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18390","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,42],"self-supervised":[1],"learning,":[2],"self-distilled":[3],"methods":[4,22],"have":[5],"shown":[6],"impressive":[7],"performance,":[8],"learning":[9,52],"representations":[10,94],"useful":[11],"for":[12],"downstream":[13,103],"tasks":[14],"and":[15,38,78,115],"even":[16,79,86],"displaying":[17],"emergent":[18],"properties.":[19],"However,":[20],"state-of-the-art":[21],"usually":[23],"rely":[24],"on":[25,102],"ensembles":[26],"of":[27,49,59,65,120],"complex":[28],"mechanisms,":[29],"with":[30,95,112],"many":[31],"design":[32],"choices":[33],"that":[34,85],"are":[35],"empirically":[36],"motivated":[37],"not":[39],"well":[40],"understood.":[41],"this":[43,87,109,129],"work,":[44],"we":[45,55],"explore":[46],"the":[47,57,126],"role":[48],"self-distillation":[50,60],"within":[51],"dynamics.":[53],"Specifically,":[54],"isolate":[56],"effect":[58,110],"by":[61,125],"training":[62],"a":[63,99,117],"group":[64],"randomly":[66],"initialized":[67],"networks,":[68],"removing":[69],"all":[70],"other":[71],"common":[72],"components":[73],"such":[74],"as":[75],"projectors,":[76],"predictors,":[77],"pretext":[80],"tasks.":[81,104],"Our":[82],"findings":[83],"show":[84],"minimal":[88],"setup":[89],"can":[90],"lead":[91],"to":[92],"learned":[93,124],"non-trivial":[96],"improvements":[97],"over":[98],"random":[100],"baseline":[101],"We":[105],"also":[106],"demonstrate":[107],"how":[108],"varies":[111],"different":[113],"hyperparameters":[114],"present":[116],"short":[118],"analysis":[119],"what":[121],"is":[122],"being":[123],"models":[127],"under":[128],"setup.":[130]},"counts_by_year":[],"updated_date":"2026-04-22T06:07:44.442478","created_date":"2026-04-22T00:00:00"}