{"id":"https://openalex.org/W4308618925","doi":"https://doi.org/10.48550/arxiv.2211.03710","title":"Graph Contrastive Learning with Implicit Augmentations","display_name":"Graph Contrastive Learning with Implicit Augmentations","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308618925","doi":"https://doi.org/10.48550/arxiv.2211.03710"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.03710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.03710","pdf_url":"https://arxiv.org/pdf/2211.03710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.03710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035381555","display_name":"Huidong Liang","orcid":"https://orcid.org/0000-0001-5960-2741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Huidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xingjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Bilei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zejun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451984","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-9457-9364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Junbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9954000115394592,"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":0.9954000115394592,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9340000152587891,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6784155964851379},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6396380066871643},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5421025156974792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43524104356765747},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4038294851779938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784155964851379},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6396380066871643},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5421025156974792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43524104356765747},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4038294851779938}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.03710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.03710","pdf_url":"https://arxiv.org/pdf/2211.03710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.03710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.03710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.03710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.03710","pdf_url":"https://arxiv.org/pdf/2211.03710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308618925.pdf","grobid_xml":"https://content.openalex.org/works/W4308618925.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626"],"abstract_inverted_index":{"Existing":[0],"graph":[1,31,71,103],"contrastive":[2,92],"learning":[3,100],"methods":[4],"rely":[5],"on":[6,10,125],"augmentation":[7],"techniques":[8],"based":[9],"random":[11],"perturbations":[12],"(e.g.,":[13],"randomly":[14],"adding":[15],"or":[16,25,119],"dropping":[17],"edges":[18,24],"and":[19,33,128],"nodes).":[20],"Nevertheless,":[21],"altering":[22],"certain":[23],"nodes":[26],"can":[27,105],"unexpectedly":[28],"change":[29],"the":[30,35,60,90,96,109,133,147,150],"characteristics,":[32],"choosing":[34],"optimal":[36],"perturbing":[37],"ratio":[38],"for":[39,89],"each":[40],"dataset":[41],"requires":[42],"onerous":[43],"manual":[44,117],"tuning.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,83],"introduce":[50],"Implicit":[51],"Graph":[52,67],"Contrastive":[53],"Learning":[54],"(iGCL),":[55],"which":[56],"utilizes":[57],"augmentations":[58,79,110],"in":[59,111,146,154],"latent":[61,81],"space":[62],"learned":[63],"from":[64,80],"a":[65],"Variational":[66],"Auto-Encoder":[68],"by":[69],"reconstructing":[70],"topological":[72],"structure.":[73],"Importantly,":[74],"instead":[75],"of":[76,98,152],"explicitly":[77],"sampling":[78],"distributions,":[82],"further":[84],"propose":[85],"an":[86,112],"upper":[87],"bound":[88],"expected":[91],"loss":[93],"to":[94,140],"improve":[95],"efficiency":[97],"our":[99],"algorithm.":[101],"Thus,":[102],"semantics":[104],"be":[106],"preserved":[107],"within":[108],"intelligent":[113],"way":[114],"without":[115],"arbitrary":[116],"design":[118],"prior":[120],"human":[121],"knowledge.":[122],"Experimental":[123],"results":[124],"both":[126],"graph-level":[127],"node-level":[129],"tasks":[130],"show":[131],"that":[132],"proposed":[134],"method":[135],"achieves":[136],"state-of-the-art":[137],"performance":[138],"compared":[139],"other":[141],"benchmarks,":[142],"where":[143],"ablation":[144],"studies":[145],"end":[148],"demonstrate":[149],"effectiveness":[151],"modules":[153],"iGCL.":[155]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}