{"id":"https://openalex.org/W4409657277","doi":"https://doi.org/10.1145/3696410.3714661","title":"SEHG: Bridging Interpretability and Prediction in Self-Explainable Heterogeneous Graph Neural Networks","display_name":"SEHG: Bridging Interpretability and Prediction in Self-Explainable Heterogeneous Graph Neural Networks","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657277","doi":"https://doi.org/10.1145/3696410.3714661"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714661","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","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/10.1145/3696410.3714661","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103082016","display_name":"Zhenhua Huang","orcid":"https://orcid.org/0000-0003-3178-9721"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Huang","raw_affiliation_strings":["Anhui University, Hefei, Anhui, China, University of Science and Technology of China, Hefei, Anhui, China, and Institute of Dataspace, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3178-9721","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, Anhui, China, University of Science and Technology of China, Hefei, Anhui, China, and Institute of Dataspace, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhao Zhou","orcid":"https://orcid.org/0009-0000-0413-4282"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Zhou","raw_affiliation_strings":["Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0000-0413-4282","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yufeng Li","orcid":"https://orcid.org/0009-0004-7298-9839"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Li","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0004-7298-9839","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101259051","display_name":"Xiuyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuyang Wu","raw_affiliation_strings":["Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-6687-568X","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002596064","display_name":"Chengpei Xu","orcid":"https://orcid.org/0000-0001-8860-7701"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengpei Xu","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8860-7701","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067289821","display_name":"Junfeng Fang","orcid":"https://orcid.org/0000-0002-3317-2103"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junfeng Fang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3317-2103","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017935525","display_name":"Zhaohong Jia","orcid":"https://orcid.org/0000-0001-6607-7025"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohong Jia","raw_affiliation_strings":["Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6607-7025","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000969982","display_name":"Linyuan L\u00fc","orcid":"https://orcid.org/0000-0002-2156-0432"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyuan L\u00fc","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-2156-0432","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089615958","display_name":"Feng Xia","orcid":"https://orcid.org/0000-0002-8324-1859"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Xia","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8324-1859","affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92259517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1292","last_page":"1304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973000288009644,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9957000017166138,"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/interpretability","display_name":"Interpretability","score":0.9401724338531494},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8311370611190796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7480171918869019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4606274664402008},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4521099627017975},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41554608941078186},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3764382302761078},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3439478874206543},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20572376251220703}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9401724338531494},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8311370611190796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480171918869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4606274664402008},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4521099627017975},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41554608941078186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3764382302761078},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3439478874206543},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20572376251220703}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714661","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714661","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2623300173","display_name":null,"funder_award_id":"2022ZD0211400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2659616207","display_name":null,"funder_award_id":"T2293771","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5197782107","display_name":"\u9762\u5411\u5ba2\u6237\u9700\u6c42\u7684\u667a\u80fd\u670d\u52a1\u5355\u5143\u52a8\u6001\u96c6\u6210\u4f18\u5316\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"71971002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6059964893","display_name":null,"funder_award_id":"STI 2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657277.pdf","grobid_xml":"https://content.openalex.org/works/W4409657277.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2094728533","https://openalex.org/W2743681928","https://openalex.org/W2911286998","https://openalex.org/W2965857891","https://openalex.org/W2980025636","https://openalex.org/W2990138404","https://openalex.org/W3000120900","https://openalex.org/W3012871709","https://openalex.org/W3093206758","https://openalex.org/W3103717137","https://openalex.org/W3108202858","https://openalex.org/W3116637551","https://openalex.org/W3157999218","https://openalex.org/W3207981989","https://openalex.org/W3215430231","https://openalex.org/W4211125578","https://openalex.org/W4285378361","https://openalex.org/W4287642280","https://openalex.org/W4312106615","https://openalex.org/W4313423347","https://openalex.org/W4321479942","https://openalex.org/W4382202833","https://openalex.org/W4382461866","https://openalex.org/W4386012748","https://openalex.org/W4387008453","https://openalex.org/W4387618416","https://openalex.org/W4387849006","https://openalex.org/W4389945727","https://openalex.org/W4402773128","https://openalex.org/W6786048916"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Heterogeneous":[0,72],"Graph":[1,73],"Neural":[2,74],"Networks":[3],"(HGNNs)":[4],"are":[5,149],"extensively":[6],"applied":[7],"in":[8,189,221],"modeling":[9],"web-based":[10],"applications":[11],"that":[12,80,121,239],"involve":[13],"heterogeneous":[14,62,139,167,176,245],"graph":[15,246],"structures.":[16],"Explanation":[17],"models":[18,57],"for":[19,127],"HGNNs":[20,32],"aim":[21],"to":[22,34,170,199,213,227],"address":[23,65],"their":[24],"''black":[25],"box''":[26],"nature.":[27],"Enhancing":[28],"the":[29,52,85,118,181,217],"interpretability":[30],"of":[31,88,165,183,197,211],"leads":[33],"a":[35,70,77,113,152,163,234],"better":[36],"understanding":[37],"and":[38,134,144,172,215,248],"can":[39],"potentially":[40],"improve":[41],"predictive":[42],"performance.":[43],"However,":[44],"existing":[45],"post-hoc":[46],"HGNN":[47,89,237],"explanation":[48,82,222,247],"methods":[49,120],"cannot":[50],"impact":[51],"HGNN's":[53],"predictions.":[54],"Self-explainable":[55],"homogeneous":[56],"also":[58,202],"perform":[59],"poorly":[60],"on":[61,98,123,206,243],"graphs.":[63,177],"To":[64,141,229],"these":[66,147],"challenges,":[67],"we":[68,160],"present":[69],"Self-Explainable":[71],"Network":[75],"(SEHG),":[76],"novel":[78],"architecture":[79],"integrates":[81],"generation":[83],"into":[84],"learning":[86,115],"process":[87],"through":[90],"two":[91],"alternative":[92],"stages.":[93],"The":[94,106],"first":[95],"stage":[96,108],"focuses":[97],"producing":[99],"high-quality":[100,143],"explanations":[101,136,174],"while":[102],"providing":[103],"predictions":[104],"alongside.":[105],"second":[107],"enhances":[109],"prediction":[110,249],"accuracy":[111],"by":[112,137,151,194,225],"contrastive":[114],"strategy.":[116],"Unlike":[117],"current":[119],"rely":[122],"manually":[124],"defined":[125],"metapaths":[126],"structural":[128],"explanations,":[129],"SEHG":[130,201,232],"generates":[131],"important":[132],"structure":[133],"feature":[135],"learnable":[138],"masks.":[140],"ensure":[142],"sparsity":[145],"explanation,":[146],"masks":[148],"regulated":[150],"uniquely":[153],"designed":[154,169],"range-based":[155],"penalty":[156],"during":[157],"training.":[158],"Moreover,":[159],"introduce":[161],"HetBA,":[162],"collection":[164],"synthetic":[166,207],"datasets":[168,208],"quantify":[171],"visualize":[173],"or":[175],"Extensive":[178],"experiments":[179],"demonstrate":[180],"effectiveness":[182],"SEHG,":[184],"which":[185],"surpasses":[186],"strong":[187],"baselines":[188],"real-world":[190],"node":[191],"classification":[192],"tasks":[193],"notable":[195],"margins":[196],"up":[198,212,226],"3.91%.":[200],"achieves":[203,240],"state-of-the-art":[204,241],"performance":[205,242],"with":[209],"improvement":[210],"9.44%,":[214],"records":[216],"highest":[218],"fidelity":[219],"scores":[220],"tasks,":[223],"improving":[224],"46.57%.":[228],"our":[230],"knowledge,":[231],"is":[233],"pioneering":[235],"self-explainable":[236],"framework":[238],"both":[244],"tasks.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}