{"id":"https://openalex.org/W6960222269","doi":"https://doi.org/10.11588/heidok.00033753","title":"Learning Neural Graph Representations in Non-Euclidean Geometries","display_name":"Learning Neural Graph Representations in Non-Euclidean Geometries","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6960222269","doi":"https://doi.org/10.11588/heidok.00033753"},"language":"en","primary_location":{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33753","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lopez, Federico Jorge","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lopez, Federico Jorge","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67756558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10733","display_name":"Wheat and Barley Genetics and Pathology","score":0.7452999949455261,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10733","display_name":"Wheat and Barley Genetics and Pathology","score":0.7452999949455261,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10012","display_name":"Genetic diversity and population structure","score":0.0364999994635582,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10434","display_name":"Chromosomal and Genetic Variations","score":0.02669999934732914,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.6399999856948853},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6065999865531921},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4731000065803528},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.4422999918460846},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4309999942779541},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42480000853538513},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3982999920845032},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.6399999856948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607699990272522},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5180000066757202},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4731000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643000066280365},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25870001316070557},{"id":"https://openalex.org/C157406716","wikidata":"https://www.wikidata.org/wiki/Q4115842","display_name":"Topological graph theory","level":5,"score":0.25609999895095825},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33753","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"doi:10.11588/heidok.00033753","is_oa":true,"landing_page_url":"https://doi.org/10.11588/heidok.00033753","pdf_url":null,"source":{"id":"https://openalex.org/S7407051545","display_name":"University Library Heidelberg","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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-journal"}],"best_oa_location":{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33753","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,43,85,128,321],"success":[1],"of":[2,12,20,45,53,83,107,130,151,184,188,206,211,220,259,290,334,373,408,441],"Deep":[3],"Learning":[4,47],"methods":[5],"is":[6,48,155],"heavily":[7],"dependent":[8],"on":[9,148,326,345,367,411,417,422],"the":[10,13,21,51,103,137,149,152,182,186,189,204,207,212,218,221,257,280,288,335,359,401,409,427,439,460],"choice":[11,129],"data":[14,35,71,111,138],"representation.":[15],"For":[16],"that":[17,37,73,192,283,305,377,383],"reason,":[18],"much":[19],"actual":[22],"effort":[23],"goes":[24],"into":[25,120,270,438],"Representation":[26,46],"Learning,":[27],"which":[28],"seeks":[29],"to":[30,49,88,94,102,135,203,248,262,292,340,343,357,363,394,397,429],"design":[31],"preprocessing":[32],"pipelines":[33],"and":[34,59,105,164,278,315,350,432,456],"transformations":[36],"can":[38,195,226],"support":[39],"effective":[40],"learning":[41,157],"algorithms.":[42],"aim":[44],"facilitate":[50],"task":[52],"extracting":[54],"useful":[55],"information":[56,269],"for":[57,297],"classifiers":[58],"other":[60],"predictor":[61],"models.":[62],"In":[63,191],"this":[64,108,268,454],"regard,":[65],"graphs":[66,91,240,251,346],"arise":[67],"as":[68,75,387,389],"a":[69,80,124,131,140,145,174,197,231,235,303,312,331,354,380,405],"convenient":[70],"structure":[72,126,219],"serves":[74],"an":[76,98,271],"intermediary":[77],"representation":[78],"in":[79,97,112,161,168,318,400,453],"wide":[81],"range":[82],"problems.":[84],"predominant":[86],"approach":[87],"work":[89,344],"with":[90,123,144,181,230,241,330,347,459],"has":[92],"been":[93],"embed":[95,136],"them":[96,393],"Euclidean":[99,386,431],"space,":[100],"due":[101],"power":[104],"simplicity":[106],"geometry.":[109],"Nevertheless,":[110],"many":[113],"domains":[114],"exhibit":[115],"non-Euclidean":[116,162,222],"features,":[117],"making":[118],"embeddings":[119,277,310,366],"Riemannian":[121],"manifolds":[122,342],"richer":[125],"necessary.":[127],"metric":[132],"space":[133,201,440],"where":[134],"imposes":[139],"geometric":[141,213],"inductive":[142,214],"bias,":[143],"direct":[146],"impact":[147],"performance":[150,282],"models.
\\nThis":[153],"thesis":[154],"about":[156],"neural":[158,224],"graph":[159,179,276,309,365,435],"representations":[160,295],"geometries":[163],"showcasing":[165,414],"their":[166,415],"applicability":[167],"different":[169,178,246,298,418],"downstream":[170,299],"tasks.":[171,300],"We":[172,244,301,352,403,425],"introduce":[173,302],"toolkit":[175],"formed":[176],"by":[177,217],"metrics":[180],"goal":[183],"characterizing":[185],"topology":[187],"data.":[190],"way,":[193],"we":[194,238,266,286,338,420,450],"choose":[196],"suitable":[198],"target":[199],"embedding":[200,436],"aligned":[202],"shape":[205],"dataset.":[208],"By":[209],"virtue":[210],"bias":[215],"provided":[216],"manifolds,":[223],"models":[225,437],"achieve":[227],"higher":[228,281],"performances":[229],"reduced":[232],"parameter":[233,336],"footprint.
\\nAs":[234],"first":[236],"step,":[237],"study":[239],"hierarchical":[242,250,294],"structures.":[243],"develop":[245,451],"techniques":[247],"derive":[249],"from":[252,311],"large":[253],"label":[254,313],"inventories.":[255],"Noticing":[256],"capacity":[258],"hyperbolic":[260,275,319,390,433],"spaces":[261,371],"represent":[263],"tree-like":[264],"arrangements,":[265],"incorporate":[267],"NLP":[272],"model":[273,304,322],"through":[274],"showcase":[279],"they":[284,378],"enable.
\\nSecond,":[285],"tackle":[287],"question":[289],"how":[291],"learn":[293,364],"suited":[296],"jointly":[306],"learns":[307],"task-specific":[308],"inventory":[314],"performs":[316],"classification":[317],"space.":[320],"achieves":[323],"state-of-the-art":[324],"results":[325],"very":[327],"fine-grained":[328],"labels,":[329],"remarkable":[332],"reduction":[333],"size.
\\nNext,":[337],"move":[339],"matrix":[341],"diverse":[348],"structures":[349],"properties.":[351],"propose":[353],"general":[355],"framework":[356,410],"implement":[358],"mathematical":[360],"tools":[361],"required":[362],"symmetric":[368,442],"spaces.":[369],"These":[370],"are":[372],"particular":[374],"interest":[375],"given":[376],"have":[379],"compound":[381],"geometry":[382,455],"simultaneously":[384],"contains":[385],"well":[388],"subspaces,":[391],"allowing":[392],"automatically":[395],"adapt":[396],"dissimilar":[398],"features":[399],"graph.":[402],"demonstrate":[404],"concrete":[406],"implementation":[407],"Siegel":[412],"spaces,":[413],"versatility":[416],"tasks.
\\nFinally,":[419],"focus":[421],"multi-relational":[423,434],"graphs.":[424],"devise":[426],"means":[428],"translate":[430],"positive":[443],"definite":[444],"(SPD)":[445],"matrices.":[446],"To":[447],"do":[448],"so":[449],"gyrocalculus":[452],"integrate":[457],"it":[458],"aforementioned":[461],"framework.":[462]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}