{"id":"https://openalex.org/W7128480909","doi":"https://doi.org/10.48550/arxiv.2602.08592","title":"TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models","display_name":"TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128480909","doi":"https://doi.org/10.48550/arxiv.2602.08592"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.08592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.08592","pdf_url":"https://arxiv.org/pdf/2602.08592","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.08592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125490350","display_name":"Tianyin Liao","orcid":"https://orcid.org/0009-0004-4662-5740","observed_orcids":["https://orcid.org/0009-0004-4662-5740"]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liao, Tianyin","raw_affiliation_strings":["Nankai University Binhai New Area , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University Binhai New Area , Tianjin , China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125514466","display_name":"Chunyu Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Chunyu","raw_affiliation_strings":["Nankai University Binhai New Area , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University Binhai New Area , Tianjin , China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041756873","display_name":"Yicheng Sui","orcid":"https://orcid.org/0000-0001-9763-7435","observed_orcids":["https://orcid.org/0000-0001-9763-7435"]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sui, Yicheng","raw_affiliation_strings":["Nankai University Binhai New Area , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University Binhai New Area , Tianjin , China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001590631","display_name":"Xingxuan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Xingxuan","raw_affiliation_strings":["Tsinghua University Haidian District , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian District , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cui, Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Peng","raw_affiliation_strings":["Tsinghua University Haidian District , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian District , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125536052","display_name":"Jianxin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jianxin","raw_affiliation_strings":["Beihang University Haidian District , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University Haidian District , Beijing , China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100442615","display_name":"Ziwei Zhang","orcid":"https://orcid.org/0000-0002-6194-2419","observed_orcids":["https://orcid.org/0000-0002-6194-2419","https://orcid.org/0000-0003-2451-843X"]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Ziwei","raw_affiliation_strings":["Beihang University Haidian District , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University Haidian District , Beijing , China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10203","display_name":"Recommender Systems and Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/link-prediction","display_name":"link prediction","score":0.9929999709129333},{"id":"https://openalex.org/keywords/tabular-foundation-models","display_name":"tabular foundation models","score":0.9470000267028809},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/graph-foundation-models","display_name":"graph foundation models","score":0.7210000157356262},{"id":"https://openalex.org/keywords/cross-domain-transfer","display_name":"cross-domain transfer","score":0.6119999885559082},{"id":"https://openalex.org/keywords/structural-causal-models","display_name":"structural causal models","score":0.765999972820282},{"id":"https://openalex.org/keywords/synthetic-tabular-data","display_name":"synthetic tabular data","score":0.5989999771118164},{"id":"https://openalex.org/keywords/graph-learning","display_name":"graph learning","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6725999712944031},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5346999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.08592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.08592","pdf_url":"https://arxiv.org/pdf/2602.08592","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.08592","doi":"https://doi.org/10.48550/arxiv.2602.08592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08592","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.08592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.08592","pdf_url":"https://arxiv.org/pdf/2602.08592","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128480909.pdf","grobid_xml":"https://content.openalex.org/works/W7128480909.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391799400","https://openalex.org/W4416017011","https://openalex.org/W4404340665","https://openalex.org/W4412888220","https://openalex.org/W4399511852","https://openalex.org/W4401863661","https://openalex.org/W4414566137","https://openalex.org/W2742503211","https://openalex.org/W4384807745","https://openalex.org/W7084093108"],"abstract_inverted_index":{"Link":[0,154],"prediction":[1,32,87,125,168],"is":[2],"a":[3,39,180,199],"fundamental":[4],"task":[5],"in":[6,84],"graph":[7,233],"machine":[8],"learning":[9,115,161],"with":[10,42],"widespread":[11],"applications":[12],"such":[13,130],"as":[14,131,213],"recommendation":[15],"systems,":[16],"drug":[17],"discovery,":[18],"knowledge":[19],"graphs,":[20],"etc.":[21],"In":[22],"the":[23,59,77,135,159,216,221,239],"foundation":[24,81],"model":[25],"era,":[26],"how":[27,132],"to":[28,133,157,165,185,204,223],"develop":[29,179],"universal":[30,86,200],"link":[31,124,167,202,211,225],"methods":[33,61],"across":[34,88,169,235],"datasets":[35,105],"and":[36,54,111,138,192,209],"domains":[37,237],"becomes":[38],"key":[40],"problem,":[41],"some":[43],"initial":[44],"attempts":[45],"adopting":[46],"Graph":[47,51],"Foundation":[48,151],"Models":[49],"utilizing":[50],"Neural":[52],"Networks":[53],"Large":[55],"Language":[56],"Models.":[57],"However,":[58],"existing":[60],"face":[62],"notable":[63],"limitations,":[64],"including":[65],"limited":[66],"pre-training":[67],"scale":[68],"or":[69],"heavy":[70],"reliance":[71],"on":[72,102,231],"textual":[73,118],"information.":[74,142],"Motivated":[75],"by":[76,97],"success":[78],"of":[79,117,163,241],"tabular":[80,90],"models":[82,110],"(TFMs)":[83],"achieving":[85],"diverse":[89,103,170,236],"datasets,":[91],"we":[92,147,177,197,219],"explore":[93],"an":[94],"alternative":[95],"approach":[96],"TFMs,":[98],"which":[99],"are":[100],"pre-trained":[101],"synthetic":[104],"sampled":[106],"from":[107],"structural":[108],"causal":[109],"support":[112],"strong":[113],"in-context":[114,160,228],"independent":[116],"attributes.":[119],"Nevertheless,":[120],"adapting":[121],"TFMs":[122,164],"for":[123,153,215],"faces":[126],"severe":[127],"technical":[128],"challenges":[129],"obtain":[134],"necessary":[136],"context":[137,183,187],"capture":[139,205],"link-centric":[140,206],"topological":[141,207],"To":[143],"solve":[144],"these":[145],"challenges,":[146],"propose":[148],"TFMLinker":[149],"(Tabular":[150],"Model":[152],"Predictor),":[155],"aiming":[156],"leverage":[158],"capabilities":[162],"perform":[166],"graphs":[171],"without":[172,247],"requiring":[173,248],"dataset-specific":[174,249],"fine-tuning.":[175],"Specifically,":[176],"first":[178],"prototype-augmented":[181],"local-global":[182],"module":[184],"construct":[186],"that":[188],"captures":[189],"both":[190],"graph-specific":[191],"cross-graph":[193],"transferable":[194],"patterns.":[195],"Next,":[196],"design":[198],"topology-aware":[201],"encoder":[203],"information":[208],"generate":[210],"representations":[212],"inputs":[214],"TFM.":[217],"Finally,":[218],"employ":[220],"TFM":[222],"predict":[224],"existence":[226],"through":[227],"learning.":[229],"Experiments":[230],"6":[232],"benchmarks":[234],"demonstrate":[238],"superiority":[240],"our":[242],"method":[243],"over":[244],"state-of-the-art":[245],"baselines":[246],"finetuning.":[250]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-11T00:00:00"}