{"id":"https://openalex.org/W7127302747","doi":"https://doi.org/10.48550/arxiv.2602.00596","title":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","display_name":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7127302747","doi":"https://doi.org/10.48550/arxiv.2602.00596"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.00596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009355682","display_name":"Govind Waghmare","orcid":"https://orcid.org/0000-0002-2953-1847"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Waghmare, Govind","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093646403","display_name":"Srini Rohan Gujulla Leel","orcid":"https://orcid.org/0009-0008-6486-7021"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leel, Srini Rohan Gujulla","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093335915","display_name":"Nikhil Tumbde","orcid":"https://orcid.org/0009-0005-3559-6515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tumbde, Nikhil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093643165","display_name":"B G Sumedh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G, Sumedh B","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106355128","display_name":"Sonia Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Sonia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085995102","display_name":"Srikanta Bedathur","orcid":"https://orcid.org/0000-0002-3949-2175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bedathur, Srikanta","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009355682"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9358999729156494,"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":0.9358999729156494,"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":0.0142000000923872,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6037999987602234},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5446000099182129},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4602000117301941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42820000648498535},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828999757766724},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.00596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.00596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00596","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.00596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Temporal":[0,118],"Graph":[1],"Neural":[2],"Networks":[3],"(TGNNs)":[4],"aim":[5],"to":[6,39,95,166],"capture":[7,96],"the":[8,143,171],"evolving":[9],"structure":[10],"and":[11,35,84,100,137,148,150,158,174,186],"timing":[12],"of":[13,131,146],"interactions":[14,61],"in":[15,70,191],"dynamic":[16],"graphs.":[17],"Although":[18],"many":[19],"models":[20,93],"incorporate":[21],"time":[22],"through":[23],"encodings":[24],"or":[25,65],"architectural":[26],"design,":[27],"they":[28,50],"often":[29],"compute":[30],"attention":[31,72,75,122],"over":[32,170,176],"entangled":[33],"node":[34,82],"edge":[36,56,88,126],"representations,":[37],"failing":[38],"reflect":[40,58],"their":[41],"distinct":[42,144],"temporal":[43,98,106],"behaviors.":[44],"Node":[45],"embeddings":[46],"evolve":[47],"slowly":[48,80],"as":[49],"aggregate":[51],"long-term":[52],"structural":[53],"context,":[54],"while":[55],"features":[57,127],"transient,":[59],"timestamped":[60],"(e.g.":[62],"messages,":[63],"trades,":[64],"transactions).":[66],"This":[67,110],"mismatch":[68],"results":[69],"semantic":[71],"blurring,":[73],"where":[74],"weights":[76],"cannot":[77],"distinguish":[78],"between":[79],"drifting":[81],"states":[83],"rapidly":[85],"changing,":[86],"information-rich":[87],"interactions.":[89],"As":[90],"a":[91,120,129],"result,":[92],"struggle":[94],"fine-grained":[97],"dependencies":[99],"provide":[101],"limited":[102],"transparency":[103],"into":[104],"how":[105],"relevance":[107],"is":[108],"computed.":[109],"paper":[111],"introduces":[112],"KEAT":[113,141],"(Kernelized":[114],"Edge":[115],"Attention":[116],"for":[117],"Graphs),":[119],"novel":[121],"formulation":[123],"that":[124],"modulates":[125],"using":[128],"family":[130],"continuous-time":[132],"kernels,":[133],"including":[134],"Laplacian,":[135],"RBF,":[136],"learnable":[138],"MLP":[139],"variant.":[140],"preserves":[142],"roles":[145],"nodes":[147],"edges,":[149],"integrates":[151],"seamlessly":[152],"with":[153],"both":[154],"Transformer-style":[155],"(e.g.,":[156,160],"DyGFormer)":[157],"message-passing":[159],"TGN)":[161],"architectures.":[162],"It":[163],"achieves":[164],"up":[165],"18%":[167],"MRR":[168],"improvement":[169],"recent":[172],"DyGFormer":[173],"7%":[175],"TGN":[177],"on":[178],"link":[179],"prediction":[180],"tasks,":[181],"enabling":[182],"more":[183],"accurate,":[184],"interpretable":[185],"temporally":[187],"aware":[188],"message":[189],"passing":[190],"TGNNs.":[192]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-04T00:00:00"}