{"id":"https://openalex.org/W7156888723","doi":"https://doi.org/10.48550/arxiv.2604.24374","title":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","display_name":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156888723","doi":"https://doi.org/10.48550/arxiv.2604.24374"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.24374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134796446","display_name":"Phung Gia Huy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy, Phung Gia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133634955","display_name":"Hai An Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu, Hai An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133718120","display_name":"Minh-Phuc Truong","orcid":"https://orcid.org/0009-0005-3834-4882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Truong, Minh-Phuc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134802999","display_name":"Thang Duc Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Thang Duc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125251729","display_name":"Linh Ngo Van","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van, Linh Ngo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046079137","display_name":"T. JoAnna Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Thanh Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134800191","display_name":"Trung Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Trung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.42649999260902405,"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":0.42649999260902405,"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":0.28380000591278076,"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/T10028","display_name":"Topic Modeling","score":0.08229999989271164,"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/chaining","display_name":"Chaining","score":0.7117000222206116},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6337000131607056},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6327000260353088},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5091000199317932},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47929999232292175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/nesting","display_name":"Nesting (process)","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480000257492065},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.7117000222206116},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5957000255584717},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449000060558319},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C2776937656","wikidata":"https://www.wikidata.org/wiki/Q2229669","display_name":"Nesting (process)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Representation":[0,19,55],"learning":[1,31],"is":[2,16,40],"fundamental":[3],"to":[4,70,144],"NLP,":[5],"but":[6],"building":[7],"embeddings":[8],"that":[9,120,148,153],"work":[10],"well":[11],"at":[12],"different":[13],"computational":[14],"budgets":[15],"challenging.":[17],"Matryoshka":[18,77,151],"Learning":[20,56],"(MRL)":[21],"offers":[22],"a":[23,65,116],"flexible":[24],"inference":[25],"paradigm":[26],"through":[27,84],"nested":[28],"embeddings;":[29],"however,":[30],"such":[32],"structures":[33],"requires":[34],"explicit":[35],"coordination":[36],"of":[37],"how":[38],"information":[39],"arranged":[41],"across":[42,157],"embedding":[43],"dimensionality":[44],"and":[45,61,74,93,98,137],"model":[46],"depth.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"propose":[52],"MIPIC":[53,79,149],"(Matryoshka":[54],"via":[57,111],"Self-Distilled":[58,85],"Intra-Relational":[59,86],"Alignment":[60,87],"Progressive":[62,112],"Information":[63,113],"Chaining),":[64],"unified":[66],"training":[67],"framework":[68],"designed":[69],"produce":[71],"structurally":[72],"coherent":[73],"semantically":[75],"compact":[76],"representations.":[78],"promotes":[80],"cross-dimensional":[81],"structural":[82],"consistency":[83],"(SIA),":[88],"which":[89],"aligns":[90],"token-level":[91],"geometric":[92],"attention-driven":[94],"relations":[95],"between":[96],"full":[97],"truncated":[99],"representations":[100,152],"using":[101],"top-k":[102],"CKA":[103],"self-distillation.":[104],"Complementarily,":[105],"it":[106],"enables":[107],"depth-wise":[108],"semantic":[109],"consolidation":[110],"Chaining":[114],"(PIC),":[115],"scaffolded":[117],"alignment":[118],"strategy":[119],"incrementally":[121],"transfers":[122],"mature":[123],"task":[124],"semantics":[125],"from":[126,142],"deeper":[127],"layers":[128],"into":[129],"earlier":[130],"layers.":[131],"Extensive":[132],"experiments":[133],"on":[134],"STS,":[135],"NLI,":[136],"classification":[138],"benchmarks":[139],"(spanning":[140],"models":[141],"TinyBERT":[143],"BGEM3,":[145],"Qwen3)":[146],"demonstrate":[147],"yields":[150],"are":[154],"highly":[155],"competitive":[156],"all":[158],"capacities,":[159],"with":[160],"significant":[161],"performance":[162],"advantages":[163],"observed":[164],"under":[165],"extreme":[166],"low-dimensional.":[167]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}