{"id":"https://openalex.org/W7225797866","doi":"https://doi.org/10.3390/sym18111883","title":"SymPath: Symmetric Path Retrieval with Multi-Grained Semantic Alignment for Knowledge Graph Question Answering","display_name":"SymPath: Symmetric Path Retrieval with Multi-Grained Semantic Alignment for Knowledge Graph Question Answering","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225797866","doi":"https://doi.org/10.3390/sym18111883"},"language":"en","primary_location":{"id":"doi:10.3390/sym18111883","doi":"https://doi.org/10.3390/sym18111883","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111883","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/sym18111883","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040389745","display_name":"Xuezhang Mao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuezhang Mao","raw_affiliation_strings":["School of Naval Architecture and Ocean Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China"],"raw_orcid":"https://orcid.org/0000-0003-2418-1603","affiliations":[{"raw_affiliation_string":"School of Naval Architecture and Ocean Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134704603","display_name":"Dongqi Han","orcid":"https://orcid.org/0009-0009-5404-4280","observed_orcids":["https://orcid.org/0009-0009-5404-4280"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dongqi Han","raw_affiliation_strings":["Jiangsu Modern Shipbuilding Technology Co., Ltd., Zhenjiang 212003, China"],"raw_orcid":"https://orcid.org/0009-0009-5404-4280","affiliations":[{"raw_affiliation_string":"Jiangsu Modern Shipbuilding Technology Co., Ltd., Zhenjiang 212003, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060508252","display_name":"Jucheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jucheng Wang","raw_affiliation_strings":["School of Naval Architecture and Ocean Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Naval Architecture and Ocean Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161442350","display_name":"Jian Xue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["Jiangsu Modern Shipbuilding Technology Co., Ltd., Zhenjiang 212003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Modern Shipbuilding Technology Co., Ltd., Zhenjiang 212003, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128953974","display_name":"Tongtong Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Liang","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China"],"raw_orcid":"https://orcid.org/0009-0008-4045-5495","affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5134704603"],"corresponding_institution_ids":[],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"11","first_page":"1883","last_page":"1883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.5609999895095825,"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":0.5609999895095825,"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":0.37700000405311584,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.023800000548362732,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525999784469604},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6060000061988831},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46540001034736633},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4366999864578247},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.384799987077713},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/sym18111883","doi":"https://doi.org/10.3390/sym18111883","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111883","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/sym18111883","doi":"https://doi.org/10.3390/sym18111883","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111883","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-hop":[0],"knowledge":[1],"graph":[2,54],"question":[3],"answering":[4],"(KGQA)":[5],"faces":[6],"practical":[7],"deployment":[8],"hurdles:":[9],"large":[10],"language":[11],"models":[12],"suffer":[13],"from":[14,52],"high":[15],"computational":[16],"overhead":[17],"and":[18,70,84,132,139,143,163],"hallucination":[19],"risks,":[20],"while":[21],"graph-based":[22],"methods":[23],"rely":[24],"on":[25,130,170,174],"entity-centric":[26],"subgraphs":[27],"that":[28,47,66,135],"adapt":[29],"poorly":[30],"to":[31,101,118],"dynamic":[32],"graphs.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"we":[38],"propose":[39],"SymPath,":[40],"a":[41,61,75,152,179],"lightweight":[42],"symmetric":[43,77],"path":[44],"retrieval":[45,51],"method":[46],"decouples":[48],"neural":[49],"semantic":[50,78],"symbolic":[53],"execution.":[55],"Leveraging":[56],"architectural":[57],"symmetry,":[58],"SymPath":[59,136,156],"employs":[60],"parameter-shared":[62],"22-million-parameter":[63],"dual-tower":[64],"encoder":[65],"maps":[67],"natural-language":[68],"questions":[69],"candidate":[71],"relation":[72],"paths":[73],"into":[74],"unified,":[76],"space,":[79],"eliminating":[80],"the":[81,115,124],"parameter":[82],"redundancy":[83],"representation":[85],"drift":[86],"of":[87],"asymmetric":[88],"encoders.":[89],"A":[90],"multi-grained":[91],"alignment":[92],"mechanism":[93],"combines":[94],"global":[95],"mean":[96],"pooling":[97],"with":[98],"token-level":[99],"MaxSim":[100],"accurately":[102],"discriminate":[103],"multi-hop":[104],"paths,":[105],"which":[106],"are":[107],"then":[108],"executed":[109],"symbolically":[110],"without":[111,121],"free-form":[112],"generation.":[113],"Consequently,":[114],"model":[116],"adapts":[117],"updated":[119],"graphs":[120],"retraining.":[122],"Under":[123],"gold":[125],"topic":[126],"entity":[127,149],"protocol,":[128],"experiments":[129],"WebQSP":[131],"ComplexWebQuestions":[133],"show":[134],"achieves":[137,164],"67.8%":[138],"60.6%":[140],"F1,":[141],"respectively,":[142],"reaches":[144],"61.7%":[145],"Hits@1":[146],"under":[147],"random":[148],"sampling,":[150],"outperforming":[151],"110-million-parameter":[153],"baseline.":[154],"Furthermore,":[155],"requires":[157],"only":[158],"\u223c1":[159],"GB":[160],"GPU":[161],"memory":[162],"low":[165],"per-batch":[166],"latency":[167],"(300":[168],"ms":[169,173],"GPU;":[171],"530":[172],"CPU).":[175],"These":[176],"results":[177],"demonstrate":[178],"competitive":[180],"accuracy\u2013efficiency":[181],"trade-off":[182],"for":[183],"resource-constrained":[184],"KGQA.":[185]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}