{"id":"https://openalex.org/W7155774141","doi":"https://doi.org/10.1145/3774904.3792238","title":"Grasp: Refining Semantic Graphs into Purified Knowledge for Cross-Modal Communication","display_name":"Grasp: Refining Semantic Graphs into Purified Knowledge for Cross-Modal Communication","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7155774141","doi":"https://doi.org/10.1145/3774904.3792238"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792238","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792238","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134674018","display_name":"Liang Chen","orcid":"https://orcid.org/0009-0003-7256-2037"},"institutions":[{"id":"https://openalex.org/I111753288","display_name":"Fujian Normal University","ror":"https://ror.org/020azk594","country_code":"CN","type":"education","lineage":["https://openalex.org/I111753288"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Chen","raw_affiliation_strings":["Fujian Normal University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7256-2037","affiliations":[{"raw_affiliation_string":"Fujian Normal University, Fuzhou, China","institution_ids":["https://openalex.org/I111753288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017371652","display_name":"X Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I111753288","display_name":"Fujian Normal University","ror":"https://ror.org/020azk594","country_code":"CN","type":"education","lineage":["https://openalex.org/I111753288"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoding Wang","raw_affiliation_strings":["Fujian Normal University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0494-3538","affiliations":[{"raw_affiliation_string":"Fujian Normal University, Fuzhou, China","institution_ids":["https://openalex.org/I111753288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055176283","display_name":"Limei Lin","orcid":"https://orcid.org/0000-0001-7227-6258"},"institutions":[{"id":"https://openalex.org/I111753288","display_name":"Fujian Normal University","ror":"https://ror.org/020azk594","country_code":"CN","type":"education","lineage":["https://openalex.org/I111753288"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limei Lin","raw_affiliation_strings":["Fujian Normal University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7227-6258","affiliations":[{"raw_affiliation_string":"Fujian Normal University, Fuzhou, China","institution_ids":["https://openalex.org/I111753288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024044743","display_name":"Dajin Wang","orcid":"https://orcid.org/0000-0003-4247-3909"},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dajin Wang","raw_affiliation_strings":["Montclair State University, Montclair, USA"],"raw_orcid":"https://orcid.org/0000-0003-4247-3909","affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062494507","display_name":"Zhiquan Liu","orcid":"https://orcid.org/0000-0002-3934-2177"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiquan Liu","raw_affiliation_strings":["Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-2177","affiliations":[{"raw_affiliation_string":"Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134663822","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-3472-1717"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["Temple University, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0002-3472-1717","affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5134674018"],"corresponding_institution_ids":["https://openalex.org/I111753288"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95759624,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3709","last_page":"3719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6158000230789185,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6158000230789185,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.061500001698732376,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05420000106096268,"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/grasp","display_name":"GRASP","score":0.6547999978065491},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5462999939918518},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41190001368522644},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4068000018596649},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38350000977516174},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.35420000553131104},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906000018119812},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6547999978065491},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792238","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792238","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W3177376120","https://openalex.org/W3214462705","https://openalex.org/W4307076504","https://openalex.org/W4323896648","https://openalex.org/W4365420366","https://openalex.org/W4367046802","https://openalex.org/W4381735898","https://openalex.org/W4385452934","https://openalex.org/W4385691485","https://openalex.org/W4388937122","https://openalex.org/W4390017704","https://openalex.org/W4391677749","https://openalex.org/W4392152400","https://openalex.org/W4393252833","https://openalex.org/W4393371816","https://openalex.org/W4394606408","https://openalex.org/W4396712624","https://openalex.org/W4396843654","https://openalex.org/W4399272759","https://openalex.org/W4399525892","https://openalex.org/W4400409682","https://openalex.org/W4402351164","https://openalex.org/W4403296843","https://openalex.org/W4405351316","https://openalex.org/W4409069799","https://openalex.org/W4409657103","https://openalex.org/W4411171623","https://openalex.org/W4413156242","https://openalex.org/W4415593474","https://openalex.org/W4415799125"],"related_works":[],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"of":[3,34,118],"multimodal":[4,141],"web":[5,169],"data":[6],"demands":[7],"communication":[8,195],"that":[9,94,194],"transmits":[10],"meaning":[11],"rather":[12],"than":[13],"raw":[14],"bits.":[15],"Existing":[16],"semantic-communication":[17],"systems":[18,206],"often":[19],"fail":[20],"under":[21,157],"noise,":[22],"missing":[23,163],"modalities,":[24,164],"and":[25,52,91,121,173,181],"distribution":[26],"shifts":[27],"because":[28],"they":[29],"optimize":[30],"surface":[31],"features":[32],"instead":[33],"modality-invariant":[35],"knowledge.":[36],"We":[37],"present":[38],"Grasp,":[39],"a":[40,54,58,77,85,131,146],"knowledge-centric":[41],"framework":[42],"for":[43,207],"cross-modal":[44,132,171],"communication.":[45],"Grasp":[46,129],"segments":[47],"streams":[48],"into":[49],"semantic":[50,179],"blocks":[51],"builds":[53],"graph":[55],"over":[56,184],"them;":[57],"lightweight":[59],"Graph":[60],"Neural":[61],"Networks":[62],"(GNN)":[63],"produces":[64],"schedulable,":[65],"importance-weighted":[66],"representations.":[67],"At":[68,143],"its":[69],"core":[70],"is":[71,200],"knowledge":[72,137,152,177,199],"purification":[73],":":[74],"we":[75,108],"minimize":[76],"conditional":[78],"mutual":[79],"information":[80],"upper":[81],"bound":[82],"to":[83,114,153,202],"perform":[84],"three-way":[86],"disentanglement\u2014strongly":[87],"related,":[88,90],"weakly":[89],"task-irrelevant":[92],"components\u2014so":[93],"only":[95],"essential":[96],"semantics":[97,156],"are":[98,103],"transmitted":[99],"while":[100,187],"non-essential":[101],"factors":[102],"suppressed.":[104],"To":[105],"maintain":[106],"synchrony,":[107],"introduce":[109],"one-to-two":[110],"temporal":[111],"contrastive":[112],"learning":[113],"achieve":[115],"triple":[116],"alignment":[117],"video,":[119],"audio,":[120],"text":[122],"despite":[123],"sampling":[124],"asynchrony.":[125],"For":[126],"efficient":[127],"transmission,":[128],"uses":[130],"shared":[133,151],"vector-quantization":[134],"codebook\u2014a":[135],"discrete":[136],"codebook":[138],"\u2014updated":[139],"by":[140],"attention.":[142],"the":[144,208],"receiver,":[145],"soft-recovery":[147],"mechanism":[148],"leverages":[149],"this":[150],"robustly":[154],"reconstruct":[155],"low":[158,189],"signal-to-noise":[159],"ratio":[160],"(SNR)":[161],"or":[162],"yielding":[165],"graceful":[166],"degradation.":[167],"Across":[168],"tasks\u2014including":[170],"retrieval":[172],"missing-modality":[174],"inference\u2014Grasp":[175],"improves":[176],"consistency,":[178],"fidelity,":[180],"downstream":[182],"performance":[183],"strong":[185],"baselines":[186],"maintaining":[188],"latency.":[190],"These":[191],"results":[192],"show":[193],"structured":[196],"around":[197],"purified":[198],"key":[201],"building":[203],"robust,":[204],"semantic-aware":[205],"modern":[209],"web.":[210]},"counts_by_year":[],"updated_date":"2026-04-28T06:12:00.211691","created_date":"2026-04-28T00:00:00"}