{"id":"https://openalex.org/W3137018386","doi":"https://doi.org/10.1109/bigdata50022.2020.9377827","title":"An Evaluation of Backpropagation Interpretability for Graph Classification with Deep Learning","display_name":"An Evaluation of Backpropagation Interpretability for Graph Classification with Deep Learning","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3137018386","doi":"https://doi.org/10.1109/bigdata50022.2020.9377827","mag":"3137018386"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024710709","display_name":"Kenneth Teo Tian Shun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kenneth Teo Tian Shun","raw_affiliation_strings":["NTU Singapore"],"affiliations":[{"raw_affiliation_string":"NTU Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044387439","display_name":"Eko Edita Limanta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eko Edita Limanta","raw_affiliation_strings":["NTU Singapore"],"affiliations":[{"raw_affiliation_string":"NTU Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019024971","display_name":"Arijit Khan","orcid":"https://orcid.org/0000-0002-7312-6312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arijit Khan","raw_affiliation_strings":["NTU Singapore"],"affiliations":[{"raw_affiliation_string":"NTU Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024710709"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77083901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9991999864578247,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9818999767303467,"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":0.9764218330383301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7538777589797974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7498353719711304},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7368249893188477},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6636431813240051},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6568465828895569},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5888378620147705},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5505474209785461},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4720417261123657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4646892547607422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37117916345596313},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1742922067642212}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9764218330383301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7538777589797974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498353719711304},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7368249893188477},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6636431813240051},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6568465828895569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5888378620147705},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5505474209785461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4720417261123657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4646892547607422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37117916345596313},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1742922067642212}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1662382123","https://openalex.org/W2056562706","https://openalex.org/W2102039273","https://openalex.org/W2121406124","https://openalex.org/W2136316164","https://openalex.org/W2164281374","https://openalex.org/W2520469311","https://openalex.org/W2594183968","https://openalex.org/W2605409611","https://openalex.org/W2788919350","https://openalex.org/W2811124557","https://openalex.org/W2911738047","https://openalex.org/W2951659295","https://openalex.org/W2955308964","https://openalex.org/W2962790223","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963460103","https://openalex.org/W2963858333","https://openalex.org/W2963911037","https://openalex.org/W2964015378","https://openalex.org/W2964113829","https://openalex.org/W2964303497","https://openalex.org/W2965774812","https://openalex.org/W2972317931","https://openalex.org/W2979481854","https://openalex.org/W2996061341","https://openalex.org/W4293651439","https://openalex.org/W4297733535","https://openalex.org/W4298061300","https://openalex.org/W6637178625","https://openalex.org/W6638444622","https://openalex.org/W6685133223","https://openalex.org/W6685350579","https://openalex.org/W6726873649","https://openalex.org/W6734561206","https://openalex.org/W6736518430","https://openalex.org/W6744557953","https://openalex.org/W6745537798","https://openalex.org/W6748218292","https://openalex.org/W6748524405","https://openalex.org/W6753331806","https://openalex.org/W6758327135","https://openalex.org/W6767288045","https://openalex.org/W6769161880"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"The":[0],"end-to-end":[1],"learning":[2,23,97,133],"in":[3,101],"convolutional":[4,65],"neural":[5,33,66],"networks":[6,34,67],"(CNNs)":[7],"and":[8,95,109,126,138,142,162,179],"their":[9,115,136,159,177],"ability":[10],"to":[11,47],"extract":[12],"localized":[13],"deep":[14,96,132],"features,":[15],"have":[16,44],"turned":[17],"them":[18,168],"into":[19],"powerful":[20],"tools":[21],"for":[22,63,117],"from":[24,154],"a":[25],"large":[26],"corpus":[27],"of":[28,51,58,73],"data":[29,54],"including":[30],"graphs.":[31],"Deep":[32],"such":[35],"as":[36,111,113],"CNNs":[37],"are":[38],"\"black-box\",":[39],"therefore":[40],"various":[41],"interpretability":[42,62,82],"methods":[43],"been":[45],"developed":[46],"understand":[48],"which":[49],"aspects":[50],"the":[52,56,59,118,170,189],"input":[53],"drive":[55],"decisions":[57],"network.":[60],"However,":[61],"graph":[64,119,152],"(GC-NNs)":[68],"is":[69],"an":[70],"open":[71],"area":[72],"research.":[74],"To":[75],"this":[76],"end,":[77],"we":[78,157],"investigate":[79],"three":[80,104],"backpropagation-based":[81],"methods:":[83],"saliency":[84],"map":[85],"with":[86,103,114,169],"contrastive":[87],"gradients":[88],"(CG),":[89],"gradient-weighted":[90],"class":[91],"activation":[92],"mapping":[93],"(Grad-CAM),":[94],"important":[98],"features":[99],"(DeepLIFT)":[100],"conjunction":[102],"state-of-the-art":[105],"GCNNs:":[106],"GCNN+GAP,":[107],"DGCNN,":[108],"DIFFPOOL,":[110],"well":[112],"variants,":[116],"classification":[120],"problem.":[121],"We":[122,182],"discuss":[123],"novel":[124],"challenges":[125],"our":[127,145,186],"solutions":[128],"towards":[129],"integrating":[130],"these":[131],"frameworks,":[134],"measuring":[135],"efficiency":[137],"performance":[139],"both":[140],"qualitatively":[141],"quantitatively.":[143],"With":[144],"extensive":[146],"empirical":[147],"analysis":[148],"over":[149],"five":[150],"real-world":[151],"datasets":[153],"different":[155],"categories,":[156],"report":[158],"quantitative,":[160],"visualization,":[161],"active":[163],"subgraph":[164,173],"based":[165],"performance,":[166],"compare":[167],"classic":[171],"significant":[172],"mining":[174],"results,":[175],"summarize":[176],"trade-offs":[178],"surprising":[180],"findings.":[181],"conclude":[183],"by":[184],"discussing":[185],"recommendations":[187],"on":[188],"road":[190],"ahead.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}