{"id":"https://openalex.org/W4401863668","doi":"https://doi.org/10.1145/3637528.3671946","title":"Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction","display_name":"Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863668","doi":"https://doi.org/10.1145/3637528.3671946"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671946","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Juzheng Zhang","orcid":"https://orcid.org/0009-0002-4961-8963"},"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":"Juzheng Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4961-8963","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011537956","display_name":"Lanning Wei","orcid":"https://orcid.org/0000-0001-9184-3019"},"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":"Lanning Wei","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9184-3019","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102956776","display_name":"Zhen Xu","orcid":"https://orcid.org/0000-0002-8901-1819"},"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":"Zhen Xu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8901-1819","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072484211","display_name":"Quanming Yao","orcid":"https://orcid.org/0000-0001-8944-8618"},"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":"Quanming Yao","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8944-8618","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.2844,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93010033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4223","last_page":"4231"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.7442720532417297},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.7263611555099487},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5700099468231201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405882596969604},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4797412157058716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4516415596008301},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44529443979263306},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34923529624938965},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12445086240768433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442720532417297},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.7263611555099487},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5700099468231201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405882596969604},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4797412157058716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4516415596008301},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44529443979263306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34923529624938965},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12445086240768433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863668.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1564354600","https://openalex.org/W1888005072","https://openalex.org/W2007444087","https://openalex.org/W2026417691","https://openalex.org/W2037705937","https://openalex.org/W2039688703","https://openalex.org/W2054141820","https://openalex.org/W2154851992","https://openalex.org/W2913015533","https://openalex.org/W2962756421","https://openalex.org/W2964051675","https://openalex.org/W3104097132","https://openalex.org/W3172525852","https://openalex.org/W3195040486","https://openalex.org/W3213267662","https://openalex.org/W4224317449","https://openalex.org/W4380993339","https://openalex.org/W4390005328","https://openalex.org/W4393260925"],"related_works":["https://openalex.org/W1518185400","https://openalex.org/W3200586296","https://openalex.org/W4230332972","https://openalex.org/W1998033311","https://openalex.org/W4247322236","https://openalex.org/W4231165741","https://openalex.org/W1762272577","https://openalex.org/W4206960768","https://openalex.org/W4229899156","https://openalex.org/W2158247860"],"abstract_inverted_index":{"Link":[0],"prediction":[1,149],"is":[2,153],"a":[3,45,76,112,145,165],"fundamental":[4],"task":[5],"in":[6,22,28,148],"graph":[7,23],"learning,":[8],"inherently":[9],"shaped":[10],"by":[11,70,144],"the":[12,15,40,59,89,99,127,134,175],"topology":[13],"of":[14,42,114,138,156],"graph.":[16],"While":[17],"traditional":[18],"heuristics":[19,53,66,177],"are":[20,181],"grounded":[21],"topology,":[24],"they":[25],"encounter":[26],"challenges":[27],"generalizing":[29],"across":[30],"diverse":[31],"graphs.":[32],"Recent":[33],"research":[34],"efforts":[35],"have":[36],"aimed":[37],"to":[38,80,96,110],"leverage":[39],"potential":[41],"heuristics,":[43],"yet":[44],"unified":[46,77],"formulation":[47,79],"accommodating":[48],"both":[49,62],"local":[50,63],"and":[51,64,82,105,130,136,178],"global":[52,65],"remains":[54],"undiscovered.":[55],"Drawing":[56],"insights":[57],"from":[58],"fact":[60],"that":[61,174],"can":[67],"be":[68],"represented":[69],"adjacency":[71],"matrix":[72,78],"multiplications,":[73],"we":[74],"propose":[75,88],"accommodate":[81],"generalize":[83],"various":[84],"heuristics.":[85],"We":[86],"further":[87,172],"Heuristic":[90],"Learning":[91],"Graph":[92],"Neural":[93],"Network":[94],"(HL-GNN)":[95],"efficiently":[97],"implement":[98],"formulation.":[100],"HL-GNN":[101,152],"adopts":[102],"intra-layer":[103],"propagation":[104],"inter-layer":[106],"connections,":[107],"allowing":[108],"it":[109],"reach":[111],"depth":[113],"around":[115],"20":[116],"layers":[117],"with":[118],"lower":[119],"time":[120],"complexity":[121],"than":[122,159],"GCN.":[123],"Extensive":[124],"experiments":[125],"on":[126],"Planetoid,":[128],"Amazon,":[129],"OGB":[131],"datasets":[132],"underscore":[133],"effectiveness":[135],"efficiency":[137],"HL-GNN.":[139],"It":[140],"outperforms":[141],"existing":[142],"methods":[143,161],"large":[146],"margin":[147],"performance.":[150],"Additionally,":[151],"several":[154],"orders":[155],"magnitude":[157],"faster":[158],"heuristic-inspired":[160],"while":[162],"requiring":[163],"only":[164],"few":[166],"trainable":[167],"parameters.":[168],"The":[169],"case":[170],"study":[171],"demonstrates":[173],"generalized":[176],"learned":[179],"weights":[180],"highly":[182],"interpretable.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}