{"id":"https://openalex.org/W6945988760","doi":"https://doi.org/10.25781/kaust-di8n1","title":"Interpretable Learning on Heterogeneous Graphs","display_name":"Interpretable Learning on Heterogeneous Graphs","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6945988760","doi":"https://doi.org/10.25781/kaust-di8n1"},"language":"en","primary_location":{"id":"doi:10.25781/kaust-di8n1","is_oa":true,"landing_page_url":"https://doi.org/10.25781/kaust-di8n1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051967","display_name":"KAUST Research Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.25781/kaust-di8n1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang, Qiang","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Yang, Qiang","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71920554"],"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":true,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8761000037193298,"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":0.8761000037193298,"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":0.0892999991774559,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.00559999980032444,"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/leverage","display_name":"Leverage (statistics)","score":0.5570999979972839},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5350000262260437},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49570000171661377},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4715000092983246},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/heterogeneous-network","display_name":"Heterogeneous network","score":0.3978999853134155},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909000277519226},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091999769210815},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.3978999853134155},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.25781/kaust-di8n1","is_oa":true,"landing_page_url":"https://doi.org/10.25781/kaust-di8n1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051967","display_name":"KAUST Research Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"}],"best_oa_location":{"id":"doi:10.25781/kaust-di8n1","is_oa":true,"landing_page_url":"https://doi.org/10.25781/kaust-di8n1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051967","display_name":"KAUST Research Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0,71],"Representation":[1],"Learning":[2],"has":[3,18],"gained":[4],"substantial":[5],"attention":[6],"in":[7,192],"recent":[8],"years":[9],"within":[10,222],"the":[11,22,61,93,177,213,234,280,315,323],"field":[12],"of":[13,24,40,60,89,152,163,215,318,325],"data":[14,25],"mining.":[15],"This":[16],"interest":[17],"been":[19],"driven":[20],"by":[21,123,175,257],"prevalence":[23],"organized":[26],"as":[27,30,243],"graphs,":[28,35,54,115,224,313],"such":[29],"social":[31],"networks":[32],"and":[33,42,57,70,116,119,136,197,220,299],"academic":[34,312],"which":[36],"encompass":[37],"various":[38],"types":[39],"nodes":[41,56],"edges-forming":[43],"heterogeneous":[44,140,157,193,218,311],"graphs.":[45,141],"However,":[46,85,262],"many":[47],"existing":[48],"methods":[49,65,250,321],"primarily":[50,251],"focus":[51,128,252],"on":[52,129,139,253,309,322],"homogeneous":[53],"where":[55],"edges":[58],"are":[59,97,104],"same":[62],"type.":[63],"These":[64],"often":[66,264],"leverage":[67],"Network":[68],"Embedding":[69],"Neural":[72],"Networks":[73],"(GNNs)":[74],"to":[75,171,232,266,284,330],"learn":[76],"node":[77,201],"representations":[78,112,155],"through":[79],"a":[80,205,227,244],"message-passing":[81],"mechanism":[82],"from":[83,184,273],"neighbors.":[84],"they":[86,263],"fall":[87],"short":[88],"providing":[90],"explanations":[91,339],"for":[92,113,156,238,260,303,340],"generated":[94],"predictions.":[95,164,304,341],"There":[96],"at":[98],"least":[99],"two":[100,130],"key":[101],"challenges":[102],"we":[103,127,146,203,225,295],"faced":[105],"with:":[106],"firstly,":[107],"effectively":[108],"learning":[109,153,209],"high-quality":[110],"graph":[111,124,137,276,326],"intricate":[114],"secondly,":[117],"deciphering":[118],"comprehending":[120],"predictions":[121,285],"made":[122],"models.":[125],"Here,":[126],"graph-relevant":[131,173],"tasks,":[132],"i.e.,":[133],"relation":[134,208],"prediction":[135,281],"classification":[138],"To":[142,292],"address":[143],"these":[144,182],"challenges,":[145],"introduce":[147],"an":[148,270,274],"innovative":[149],"framework":[150,167],"capable":[151],"robust":[154,298],"graphs":[158,194],"while":[159],"offering":[160],"insightful":[161],"interpretations":[162,221,302],"Notably,":[165],"our":[166,319,334],"can":[168],"be":[169],"extended":[170],"other":[172],"tasks":[174,327],"modifying":[176],"corresponding":[178],"modules.":[179],"We":[180],"tackle":[181],"problems":[183],"three":[185],"distinct":[186],"angles.":[187],"Firstly,":[188],"acknowledging":[189],"that":[190],"meta-paths":[191],"capture":[195],"diverse":[196,310],"complementary":[198],"insights":[199],"into":[200,217],"interactions,":[202],"present":[204],"novel":[206],"interpretable":[207,249],"model.":[210],"Secondly,":[211],"recognizing":[212],"scarcity":[214],"exploration":[216],"information":[219],"temporal":[223],"devise":[226],"deep":[228],"neural":[229],"network-based":[230],"approach":[231],"parameterize":[233],"interpretation":[235],"generation":[236],"process":[237],"predicted":[239],"results,":[240,282,307],"representing":[241],"it":[242],"weighted":[245],"sub-graph.":[246],"Lastly,":[247],"current":[248],"answering":[254],"\"why\"":[255],"questions":[256],"identifying":[258],"sub-graphs":[259],"interpretation.":[261],"fail":[265],"ascertain":[267],"whether":[268],"removing":[269],"identified":[271],"sub-graph":[272],"input":[275,290],"would":[277],"inevitably":[278],"alter":[279],"leading":[283],"lacking":[286],"counterfactual":[287,301],"robustness":[288],"against":[289],"noise.":[291],"remedy":[293],"this,":[294],"propose":[296],"generating":[297],"reasonable":[300],"Our":[305],"experimental":[306],"conducted":[308],"demonstrate":[314],"superior":[316],"performance":[317,324],"proposed":[320],"when":[328],"compared":[329],"state-of-the-art":[331],"approaches.":[332],"Furthermore,":[333],"designed":[335],"models":[336],"offer":[337],"well-comprehensible":[338]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}