{"id":"https://openalex.org/W2798638367","doi":"https://doi.org/10.1145/3184558.3191523","title":"Towards Interpretation of Node Embeddings","display_name":"Towards Interpretation of Node Embeddings","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798638367","doi":"https://doi.org/10.1145/3184558.3191523","mag":"2798638367"},"language":"en","primary_location":{"id":"doi:10.1145/3184558.3191523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191523","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191523&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3191523&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026318930","display_name":"Ayushi Dalmia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ayushi Dalmia","raw_affiliation_strings":["IBM Research, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113391435","display_name":"J Ganesh","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh J","raw_affiliation_strings":["IIIT Hyderabad, IIIT, India"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, IIIT, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046755750","display_name":"Manish Gupta","orcid":"https://orcid.org/0000-0002-2843-3110"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Gupta","raw_affiliation_strings":["Microsoft, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026318930"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":2.0095,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.86654423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9731000065803528,"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/computer-science","display_name":"Computer science","score":0.6685270071029663},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5600489377975464},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5433211922645569},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5189516544342041},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5151914358139038},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.4954134225845337},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44731223583221436},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42882078886032104},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.42607322335243225},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3903292417526245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35005050897598267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685270071029663},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5600489377975464},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5433211922645569},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5189516544342041},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5151914358139038},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.4954134225845337},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44731223583221436},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42882078886032104},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.42607322335243225},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3903292417526245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35005050897598267},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3184558.3191523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191523","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191523&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3184558.3191523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191523","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191523&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798638367.pdf","grobid_xml":"https://content.openalex.org/works/W2798638367.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W143174683","https://openalex.org/W188608978","https://openalex.org/W1888005072","https://openalex.org/W2037933327","https://openalex.org/W2046253692","https://openalex.org/W2062797058","https://openalex.org/W2066459332","https://openalex.org/W2067582432","https://openalex.org/W2082063580","https://openalex.org/W2089554624","https://openalex.org/W2105543219","https://openalex.org/W2138399168","https://openalex.org/W2144182447","https://openalex.org/W2145658888","https://openalex.org/W2154851992","https://openalex.org/W2286496058","https://openalex.org/W2515741950","https://openalex.org/W2534727297","https://openalex.org/W2538371562","https://openalex.org/W2768375068","https://openalex.org/W2962756421","https://openalex.org/W3100330855","https://openalex.org/W3104097132","https://openalex.org/W3104717349","https://openalex.org/W3105705953","https://openalex.org/W4232932184","https://openalex.org/W4235345084"],"related_works":["https://openalex.org/W3036264823","https://openalex.org/W3206528106","https://openalex.org/W2123605750","https://openalex.org/W2912814903","https://openalex.org/W2088740331","https://openalex.org/W2950907416","https://openalex.org/W3038102983","https://openalex.org/W2082479932","https://openalex.org/W2932872266","https://openalex.org/W4281484020"],"abstract_inverted_index":{"Recently":[0],"there":[1],"have":[2,29],"been":[3,30],"a":[4,49,84,99,124,276,290],"large":[5],"number":[6],"of":[7,25,70,73,83,115,140,146,174,209,227],"studies":[8],"on":[9,131,156],"embedding":[10,27,230,270],"large-scale":[11],"information":[12],"networks":[13],"using":[14],"low-dimensional,":[15],"neighborhood":[16],"and":[17,154,160,167,176,200,203,238,245],"community":[18],"aware":[19],"node":[20,51,85,100,125,149,201,229,269],"representations.":[21],"Though":[22],"the":[23,63,68,111,119,129,132,171,182,192,205,214,218,228,253,262,267,286],"performance":[24,184,207],"these":[26,44,141],"models":[28,151,231],"better":[31,54],"than":[32],"traditional":[33],"methods":[34],"for":[35,55,104,186,232,243,266,275,289],"graph":[36],"mining":[37],"applications,":[38],"little":[39],"is":[40,102],"known":[41],"about":[42],"what":[43],"representations":[45,130],"encode,":[46],"or":[47],"why":[48],"particular":[50],"representation":[52,101,150],"works":[53],"certain":[56],"tasks.":[57],"Our":[58,143,224,249],"work":[59],"presented":[60],"here":[61],"constitutes":[62],"first":[64,225],"step":[65],"in":[66,79,123,260,284],"decoding":[67],"black-box":[69],"vector":[71,208],"embeddings":[72,219],"nodes":[74],"by":[75,221],"evaluating":[76],"their":[77],"effectiveness":[78],"encoding":[80],"elementary":[81,113,120,187,255],"properties":[82,114,121,173],"such":[86,196],"as":[87,197],"page":[88],"rank,":[89],"degree,":[90],"closeness":[91],"centrality,":[92],"clustering":[93],"coefficient,":[94],"etc.":[95],"We":[96,180],"believe":[97],"that":[98,165,236,252],"effective":[103],"an":[105],"application":[106],"only":[107],"if":[108],"it":[109],"encodes":[110],"application-specific":[112],"nodes.":[116],"To":[117],"unpack":[118],"encoded":[122],"representation,":[126],"we":[127],"evaluate":[128],"accuracy":[133],"with":[134,191],"which":[135],"they":[136],"can":[137],"model":[138,183,211,271,288],"each":[139,210],"properties.":[142],"extensive":[144],"study":[145,226],"three":[147],"state-of-the-art":[148],"(DeepWalk,":[152],"node2vec":[153,166,237],"LINE)":[155],"four":[157],"different":[158],"tasks":[159,190,258],"six":[161],"diverse":[162],"graphs":[163,178,247],"reveal":[164],"LINE":[168],"best":[169],"encode":[170],"network":[172],"sparse":[175,244],"dense":[177,246],"respectively.":[179,248],"correlate":[181],"obtained":[185],"property":[188,256],"prediction":[189,199,257],"high-level":[193],"downstream":[194,278,292],"applications":[195],"link":[198],"classification,":[202],"visualize":[204],"task":[206],"to":[212,272],"understand":[213],"semantic":[215],"similarity":[216],"between":[217],"learned":[220],"various":[222],"models.":[223],"outlier":[233],"detection":[234],"reveals":[235],"DeepWalk":[239],"identify":[240],"outliers":[241],"well":[242,274],"analysis":[250],"highlights":[251],"proposed":[254],"help":[259],"unearthing":[261],"important":[263],"features":[264],"responsible":[265],"given":[268,277,291],"perform":[273],"task.":[279,293],"This":[280],"understanding":[281],"would":[282],"facilitate":[283],"picking":[285],"right":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}