{"id":"https://openalex.org/W4416252167","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229011","title":"Every Hop Etched in Memory: Tokenized Graph Mamba Meets Directed Graph Learning","display_name":"Every Hop Etched in Memory: Tokenized Graph Mamba Meets Directed Graph Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252167","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229011"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029384246","display_name":"Lizhi Liu","orcid":"https://orcid.org/0000-0002-6983-4914"},"institutions":[{"id":"https://openalex.org/I4210098154","display_name":"UnionPay (China)","ror":"https://ror.org/00vg14y34","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098154"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lizhi Liu","raw_affiliation_strings":["China UnionPay,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China UnionPay,Shanghai,China","institution_ids":["https://openalex.org/I4210098154"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029384246"],"corresponding_institution_ids":["https://openalex.org/I4210098154"],"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9886999726295471,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9886999726295471,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0019000000320374966,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.00139999995008111,"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/directed-graph","display_name":"Directed graph","score":0.6068000197410583},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5817000269889832},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41519999504089355},{"id":"https://openalex.org/keywords/multigraph","display_name":"Multigraph","score":0.33399999141693115},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.32899999618530273},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3172000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C17758045","wikidata":"https://www.wikidata.org/wiki/Q2642629","display_name":"Multigraph","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2065528503","https://openalex.org/W2154851992","https://openalex.org/W2194775991","https://openalex.org/W2460760569","https://openalex.org/W2907492528","https://openalex.org/W2950278928","https://openalex.org/W2950635152","https://openalex.org/W2962756421","https://openalex.org/W2962834855","https://openalex.org/W2963235422","https://openalex.org/W2964051675","https://openalex.org/W4226373892","https://openalex.org/W4360825594","https://openalex.org/W4375869353","https://openalex.org/W4385245566","https://openalex.org/W4386869686","https://openalex.org/W4399163384","https://openalex.org/W4401857119","https://openalex.org/W4412524449"],"related_works":[],"abstract_inverted_index":{"Directionality":[0],"plays":[1],"a":[2,86,105,124],"unique":[3],"role":[4],"in":[5,41,128,166,189],"graphs,":[6],"and":[7,71,169],"its":[8,187],"absence":[9],"may":[10],"obscure":[11],"our":[12],"understanding":[13],"of":[14,75,113,137,142,160],"the":[15,34,64,73,94,99,111,140,157,182],"information":[16,116],"flow.":[17],"Recently,":[18],"we":[19,83],"have":[20],"witnessed":[21],"some":[22],"promising":[23],"efforts":[24],"focused":[25],"on":[26,153],"directed":[27,56,88],"graph":[28,42,89,101],"learning.":[29],"However,":[30],"these":[31],"approaches":[32],"inherit":[33],"over-smoothing":[35],"issues":[36],"that":[37,54],"is":[38,120,194],"commonly":[39],"encountered":[40],"convolutional":[43],"networks":[44],"(GCNs)":[45],"designed":[46],"for":[47],"undirected":[48],"settings.":[49],"Our":[50],"theoretical":[51],"analysis":[52],"reveals":[53],"existing":[55],"GCNs":[57],"suffer":[58],"from":[59,117],"vanishing":[60],"node":[61,167],"signals":[62],"as":[63,104,181],"model":[65,127,183],"deepens,":[66],"leading":[67],"to":[68,163],"catastrophic":[69],"forgetting":[70],"hindering":[72],"exploration":[74],"potential":[76],"long-range":[77],"dependencies.":[78],"To":[79],"address":[80],"this":[81],"issue,":[82],"propose":[84],"DIGRAM,":[85],"tokenized":[87],"Mamba":[90,138],"model.":[91],"It":[92],"interprets":[93],"message":[95],"passing":[96],"presented":[97],"by":[98],"magnetic":[100],"convolution":[102],"operator":[103],"token":[106],"sequence":[107],"generation":[108],"process.":[109],"With":[110],"emergence":[112],"new":[114],"tokens,":[115],"each":[118],"hop":[119],"progressively":[121],"fed":[122],"into":[123],"state":[125],"space":[126],"an":[129],"autoregressive":[130],"manner.":[131],"The":[132,192],"powerful":[133],"long-sequence":[134],"modeling":[135],"capability":[136],"ensures":[139],"retention":[141],"local":[143],"context":[144],"even":[145,178],"when":[146],"incorporating":[147],"high-order":[148],"topological":[149],"characteristics.":[150],"Extensive":[151],"experiments":[152],"real-world":[154],"datasets":[155],"validate":[156],"superior":[158],"performance":[159,180],"DIGRAM":[161,174],"compared":[162],"state-of-the-art":[164],"methods":[165],"classification":[168],"link":[170],"prediction":[171],"tasks.":[172],"Furthermore,":[173],"demonstrates":[175],"stable":[176],"or":[177],"improved":[179],"depth":[184],"increases,":[185],"confirming":[186],"effectiveness":[188],"mitigating":[190],"over-smoothing.":[191],"code":[193],"available":[195],"at":[196],"https://github.com/liulizhi1996/DIGRAM.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}