{"id":"https://openalex.org/W3081133449","doi":null,"title":"End-to-End Structure-Aware Convolutional Networks on Graphs","display_name":"End-to-End Structure-Aware Convolutional Networks on Graphs","alternate_titles":[],"publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3081133449","mag":"3081133449"},"language":"en","primary_location":{"id":"pmh:oai:opencommons.uconn.edu:dissertations-8887","doi":null,"is_oa":true,"landing_page_url":"https://opencommons.uconn.edu/dissertations/2555","pdf_url":"https://opencommons.uconn.edu/cgi/viewcontent.cgi?article=8887&context=dissertations","source":{"id":"https://openalex.org/S4306401180","display_name":"OpenCommons at University of Connecticut (University of Connecticut)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I140172145","host_organization_name":"University of Connecticut","host_organization_lineage":["https://openalex.org/I140172145"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral Dissertations","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W3081133449"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opencommons.uconn.edu/cgi/viewcontent.cgi?article=8887&context=dissertations","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chao Shang","orcid":"https://orcid.org/0000-0003-3905-4631","observed_orcids":["https://orcid.org/0000-0003-3905-4631"]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Chao Shang","raw_affiliation_strings":["Graduate School, University of Connecticut"],"raw_orcid":"https://orcid.org/0000-0003-3905-4631","affiliations":[{"raw_affiliation_string":"Graduate School, University of Connecticut","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9990000128746033,"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":0.9990000128746033,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.9509999752044678},{"id":"https://openalex.org/keywords/knowledge-graph-completion","display_name":"knowledge graph completion","score":0.7570000290870667},{"id":"https://openalex.org/keywords/molecular-graphs","display_name":"molecular graphs","score":0.5730000138282776},{"id":"https://openalex.org/keywords/qsar-prediction","display_name":"QSAR prediction","score":0.6600000262260437},{"id":"https://openalex.org/keywords/multivariate-time-series-forecasting","display_name":"multivariate time series forecasting","score":0.8820000290870667},{"id":"https://openalex.org/keywords/causal-discovery","display_name":"causal discovery","score":0.6859999895095825},{"id":"https://openalex.org/keywords/structure-learning","display_name":"structure learning","score":0.675000011920929},{"id":"https://openalex.org/keywords/edge-attention","display_name":"edge attention","score":0.6579999923706055},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.6759999990463257},{"id":"https://openalex.org/keywords/non-euclidean-data","display_name":"non-Euclidean data","score":0.7250000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5862314105033875},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4947352111339569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30268770456314087}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:opencommons.uconn.edu:dissertations-8887","doi":null,"is_oa":true,"landing_page_url":"https://opencommons.uconn.edu/dissertations/2555","pdf_url":"https://opencommons.uconn.edu/cgi/viewcontent.cgi?article=8887&context=dissertations","source":{"id":"https://openalex.org/S4306401180","display_name":"OpenCommons at University of Connecticut (University of Connecticut)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I140172145","host_organization_name":"University of Connecticut","host_organization_lineage":["https://openalex.org/I140172145"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral Dissertations","raw_type":"text"},{"id":"pmh:oai:digitalcommons.lib.uconn.edu:dissertations-8887","doi":null,"is_oa":false,"landing_page_url":"https://digitalcommons.lib.uconn.edu/dissertations/2555","pdf_url":null,"source":{"id":"https://openalex.org/S4306401180","display_name":"OpenCommons at University of Connecticut (University of Connecticut)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I140172145","host_organization_name":"University of Connecticut","host_organization_lineage":["https://openalex.org/I140172145"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral Dissertations","raw_type":"text"},{"id":"mag:3081133449","doi":null,"is_oa":false,"landing_page_url":"https://opencommons.uconn.edu/cgi/viewcontent.cgi?article=8887&context=dissertations","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:opencommons.uconn.edu:dissertations-8887","doi":null,"is_oa":true,"landing_page_url":"https://opencommons.uconn.edu/dissertations/2555","pdf_url":"https://opencommons.uconn.edu/cgi/viewcontent.cgi?article=8887&context=dissertations","source":{"id":"https://openalex.org/S4306401180","display_name":"OpenCommons at University of Connecticut (University of Connecticut)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I140172145","host_organization_name":"University of Connecticut","host_organization_lineage":["https://openalex.org/I140172145"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral Dissertations","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/W3081133449.pdf","grobid_xml":"https://content.openalex.org/works/W3081133449.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W637153065","https://openalex.org/W1498436455","https://openalex.org/W1533230146","https://openalex.org/W1614298861","https://openalex.org/W1662382123","https://openalex.org/W1988037271","https://openalex.org/W2007321142","https://openalex.org/W2008505552","https://openalex.org/W2026228805","https://openalex.org/W2046589863","https://openalex.org/W2064675550","https://openalex.org/W2080731889","https://openalex.org/W2094728533","https://openalex.org/W2112796928","https://openalex.org/W2127795553","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2171533950","https://openalex.org/W2178225550","https://openalex.org/W2184957013","https://openalex.org/W2187089797","https://openalex.org/W2250184916","https://openalex.org/W2250342289","https://openalex.org/W2269544137","https://openalex.org/W2283196293","https://openalex.org/W2290847742","https://openalex.org/W2316335231","https://openalex.org/W2406128552","https://openalex.org/W2432356473","https://openalex.org/W2463781041","https://openalex.org/W2519887557","https://openalex.org/W2529996553","https://openalex.org/W2558748708","https://openalex.org/W2565330852","https://openalex.org/W2565684601","https://openalex.org/W2577076988","https://openalex.org/W2593658258","https://openalex.org/W2594183968","https://openalex.org/W2594830834","https://openalex.org/W2604314403","https://openalex.org/W2606202972","https://openalex.org/W2606780347","https://openalex.org/W2612872092","https://openalex.org/W2618170429","https://openalex.org/W2624431344","https://openalex.org/W2735246657","https://openalex.org/W2751808960","https://openalex.org/W2755092149","https://openalex.org/W2756203131","https://openalex.org/W2759136286","https://openalex.org/W2766453196","https://openalex.org/W2774837955","https://openalex.org/W2798955995","https://openalex.org/W2807021761","https://openalex.org/W2811124557","https://openalex.org/W2889900103","https://openalex.org/W2898221481","https://openalex.org/W2901504064","https://openalex.org/W2907492528","https://openalex.org/W2908471473","https://openalex.org/W2919115771","https://openalex.org/W2924719072","https://openalex.org/W2940980190","https://openalex.org/W2946373483","https://openalex.org/W2948607799","https://openalex.org/W2950393809","https://openalex.org/W2962756421","https://openalex.org/W2963017945","https://openalex.org/W2963341956","https://openalex.org/W2963521276","https://openalex.org/W2963984147","https://openalex.org/W2964121744","https://openalex.org/W2987119394","https://openalex.org/W3011667710","https://openalex.org/W3034444248","https://openalex.org/W3048357673","https://openalex.org/W3152893301","https://openalex.org/W3154348970","https://openalex.org/W3175271685","https://openalex.org/W4241115065","https://openalex.org/W4300579117","https://openalex.org/W7223762255"],"related_works":["https://openalex.org/W2751507650","https://openalex.org/W2954284176","https://openalex.org/W2950393809","https://openalex.org/W2611552022","https://openalex.org/W2746492579","https://openalex.org/W2519887557","https://openalex.org/W2406128552","https://openalex.org/W7131287877","https://openalex.org/W2917992855","https://openalex.org/W2963017945"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,93],"networks":[2,109],"(CNNs)":[3],"are":[4,139,144],"powerful":[5],"tools":[6],"to":[7,51,68,71,96,151,193,233,278],"model":[8,198,241,257,295,379],"data":[9,28,54],"of":[10,24,49,74,80,160,248,262,282,300,319,390,397],"a":[11,21,77,119,131,165,184,211,245,254,259,267,291,329,332,335,344,363],"grid-like":[12],"structure,":[13],"such":[14,38,55],"as":[15,39,56],"image,":[16],"video,":[17],"and":[18,44,82,104,187,207,223,289,304,322,339,409],"speech.":[19],"However,":[20],"broad":[22],"range":[23],"scientific":[25],"problems":[26],"generate":[27],"that":[29,242,273,368],"naturally":[30],"lie":[31],"in":[32,183,210,285,328,400],"irregular":[33],"grids":[34],"with":[35],"non-Euclidean":[36,52],"metrics,":[37],"knowledge":[40,167,185,191,212,401],"graphs,":[41,43,69],"molecular":[42,236,287,309,404],"traffic":[45],"networks.":[46],"The":[47,61,107,157,226,312],"generalization":[48],"CNNs":[50],"structured":[53],"graphs":[57,288],"is":[58,356],"not":[59,199,357],"straightforward.":[60],"classical":[62],"convolutions":[63,99],"cannot":[64],"be":[65,111,194],"applied":[66],"directly":[67],"due":[70],"the":[72,136,148,161,173,202,217,230,239,279,297,301,317,320,352,370,377,381,388,391,395,398],"lack":[73],"global":[75],"parameterization,":[76],"common":[78],"system":[79],"coordinates,":[81],"shift-invariance":[83],"properties.":[84,293],"In":[85],"this":[86,251],"dissertation,":[87],"we":[88,361],"propose":[89,266,362],"several":[90],"structure-aware":[91],"convolutional":[92,271],"network":[94,127,272],"models":[95,143],"calculate":[97],"graph":[98,174,186,192,213,247,270,330,372,402],"efficiently":[100],"over":[101,125,394],"both":[102],"small-scale":[103,234],"large-scale":[105,166],"graphs.":[106,237,264,310],"proposed":[108,392],"can":[110,179],"trained":[112],"by":[113],"an":[114,189,340],"end-to-end":[115],"training":[116,133],"method":[117,252,367],"where":[118,135,331],"stochastic":[120],"gradient":[121],"descent":[122],"algorithm":[123],"back-propagates":[124],"all":[126],"components":[128,138],"rather":[129],"than":[130],"stage-wise":[132],"scheme":[134],"different":[137,286],"tuned":[140],"separately.":[141],"These":[142],"built":[145],"for":[146,380],"exploring":[147],"structure":[149,176,355,365,373],"information":[150],"improve":[152],"many":[153],"prediction":[154],"tasks:":[155],"(1)":[156],"first":[158,240],"part":[159,228,314],"dissertation":[162],"focuses":[163,315],"on":[164,316],"graph.":[168],"Our":[169],"new":[170,181],"approach":[171],"learns":[172,243,253,369],"connectivity":[175,353],"so":[177],"it":[178],"infer":[180],"edges":[182,283],"grow":[188],"input":[190],"more":[195],"complete.":[196],"This":[197,294],"only":[200],"utilizes":[201],"node":[203,333],"(or":[204],"entity)":[205],"attributes":[206],"edge":[208,276,341],"relations":[209],"but":[214],"also":[215],"preserves":[216],"so-called":[218],"translational":[219],"property":[220],"between":[221],"entities":[222],"relations.":[224],"(2)":[225],"second":[227],"extends":[229],"convolution":[231],"operation":[232],"hydrogen-depleted":[235],"Unlike":[238],"from":[244,258],"single":[246],"massive":[249,260],"size,":[250],"novel":[255],"graph-based":[256],"amount":[261],"small":[263],"We":[265],"consistent":[268,275],"edge-aware":[269],"determines":[274],"attentions":[277],"same":[280],"type":[281],"appearing":[284],"predicts":[290],"molecule's":[292],"exploits":[296],"general":[298],"consistency":[299],"bond":[302,305],"energies":[303],"lengths":[306],"across":[307],"various":[308],"(3)":[311],"third":[313],"exploration":[318],"correlation":[321],"causation":[323],"among":[324],"multivariate":[325,410],"time":[326,336,345,349,382,411],"series":[327,337,346,383,412],"represents":[334],"variable":[338],"indicates":[342],"if":[343],"causes":[347],"another":[348],"series.":[350],"When":[351],"(edge)":[354],"available":[358],"or":[359],"incomplete,":[360],"discrete":[364],"learning":[366],"hidden":[371],"simultaneously":[374],"when":[375],"constructing":[376],"predictive":[378],"data.":[384],"Extensive":[385],"experiments":[386],"demonstrate":[387],"advantages":[389],"techniques":[393],"state":[396],"art":[399],"completion,":[403],"quantitative":[405],"structure-activity":[406],"relationship":[407],"prediction,":[408],"forecasting.":[413]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3081133449","counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2020-09-01T00:00:00"}
