{"id":"https://openalex.org/W7161032123","doi":"https://doi.org/10.48550/arxiv.2605.12197","title":"A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning","display_name":"A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161032123","doi":"https://doi.org/10.48550/arxiv.2605.12197"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.12197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.12197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136025999","display_name":"Haibo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136070955","display_name":"Xin Eric Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136061813","display_name":"Jiaheng Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Jiaheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136068886","display_name":"Ling Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136019298","display_name":"Wenwu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Wenwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.965399980545044,"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":0.965399980545044,"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":0.008999999612569809,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.004800000227987766,"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":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5598000288009644},{"id":"https://openalex.org/keywords/graph-rewriting","display_name":"Graph rewriting","score":0.3540000021457672},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3528999984264374},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35109999775886536},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.34450000524520874},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3407000005245209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322999835014343},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5654000043869019},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.12197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.12197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.653882622718811,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Leveraging":[0],"Graph":[1,29,212],"Neural":[2],"Networks":[3],"(GNNs)":[4],"as":[5,52],"graph":[6,53,75,85,112,151,172,225],"encoders":[7,54],"and":[8,65,102,121,136,138,155,174,196,231],"aligning":[9,60],"the":[10,34,40,57,68,160,184,238],"resulting":[11],"representations":[12,62,105,129,226,236],"with":[13,39,67,106,141,159,183,228,237],"Large":[14],"Language":[15,30,213],"Models":[16,31],"(LLMs)":[17],"through":[18],"alignment":[19,113,117,164,194,200],"instruction":[20,114,189],"tuning":[21],"has":[22],"become":[23],"a":[24,95,198,210,217],"mainstream":[25],"paradigm":[26],"for":[27],"constructing":[28],"(GLMs),":[32],"combining":[33],"generalization":[35],"ability":[36,80],"of":[37,44,59,162,181],"LLMs":[38,107],"structural":[41],"modeling":[42],"capacity":[43],"GNNs.":[45],"However,":[46],"existing":[47],"GLMs":[48,101],"that":[49,130,215],"adopt":[50],"GNNs":[51],"largely":[55],"overlook":[56],"problem":[58,118],"GNN-encoded":[61,128],"across":[63,83,134],"domains":[64,135],"tasks":[66,137],"LLM":[69,185],"token":[70,186],"space":[71,187],"to":[72,81,93,108,147,192,222],"obtain":[73],"unified":[74],"tokens,":[76],"thereby":[77],"limiting":[78],"their":[79],"generalize":[82],"diverse":[84,171],"data.":[86],"To":[87,203],"bridge":[88],"this":[89],"gap,":[90],"we":[91,207],"aim":[92],"incorporate":[94],"multi-domain,":[96,110,218],"multi-task":[97,111,219],"GNN":[98,168,220],"encoder":[99,221],"into":[100],"align":[103],"its":[104],"enable":[109],"tuning.":[115],"This":[116],"remains":[119],"underexplored":[120],"poses":[122],"two":[123],"key":[124],"challenges:":[125],"1)":[126],"learning":[127],"are":[131],"simultaneously":[132],"generalizable":[133,224],"well":[139],"aligned":[140,227],"textual":[142,229],"semantics":[143],"is":[144],"difficult,":[145],"due":[146],"substantial":[148],"variations":[149],"in":[150,166],"structures,":[152],"feature":[153],"distributions,":[154],"supervision":[156],"signals,":[157],"together":[158],"lack":[161],"textual-semantic":[163],"guidance":[165],"task-specific":[167,175],"training;":[169],"2)":[170],"data":[173],"instructions":[176],"can":[177],"exhibit":[178],"different":[179],"degrees":[180],"compatibility":[182],"during":[188],"tuning,":[190],"leading":[191],"varying":[193],"difficulty":[195],"rendering":[197],"fixed":[199],"strategy":[201],"suboptimal.":[202],"tackle":[204],"these":[205,235],"challenges,":[206],"propose":[208],"UniGraphLM,":[209],"Unified":[211],"Model":[214],"incorporates":[216],"learn":[223],"semantics,":[230],"then":[232],"adaptively":[233],"aligns":[234],"LLM.":[239]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-14T00:00:00"}