{"id":"https://openalex.org/W4399836580","doi":"https://doi.org/10.48550/arxiv.2406.11884","title":"Hierarchical Compression of Text-Rich Graphs via Large Language Models","display_name":"Hierarchical Compression of Text-Rich Graphs via Large Language Models","publication_year":2024,"publication_date":"2024-06-13","ids":{"openalex":"https://openalex.org/W4399836580","doi":"https://doi.org/10.48550/arxiv.2406.11884"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.11884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11884","pdf_url":"https://arxiv.org/pdf/2406.11884","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/2406.11884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101412768","display_name":"Shichang Zhang","orcid":"https://orcid.org/0000-0003-0954-5018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shichang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101350111","display_name":"Da Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040806743","display_name":"Jiani Zhang","orcid":"https://orcid.org/0000-0003-0074-6761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100527604","display_name":"Qi Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675531","display_name":"Xiang Song","orcid":"https://orcid.org/0000-0001-5030-5054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"song, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016551629","display_name":"Soji Adeshina","orcid":"https://orcid.org/0000-0003-3945-3640"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adeshina, Soji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605036","display_name":"Christos Faloutsos","orcid":"https://orcid.org/0000-0003-2996-9790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faloutsos, Christos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karypis, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102048516","display_name":"Yizhou Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yizhou","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/T10028","display_name":"Topic Modeling","score":0.9772999882698059,"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/T10028","display_name":"Topic Modeling","score":0.9772999882698059,"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":0.9746000170707703,"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/T11269","display_name":"Algorithms and Data Compression","score":0.951200008392334,"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":0.5747551321983337},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4488893449306488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4311811327934265},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34723639488220215},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07962456345558167},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07272347807884216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5747551321983337},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4488893449306488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4311811327934265},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34723639488220215},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07962456345558167},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07272347807884216},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.11884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11884","pdf_url":"https://arxiv.org/pdf/2406.11884","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.2406.11884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.11884","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:2406.11884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11884","pdf_url":"https://arxiv.org/pdf/2406.11884","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/W4399836580.pdf","grobid_xml":"https://content.openalex.org/works/W4399836580.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Text-rich":[0],"graphs,":[1,11],"prevalent":[2],"in":[3,34,44,69,92,122,126,171,216],"data":[4],"mining":[5],"contexts":[6],"like":[7],"e-commerce":[8,202],"and":[9,83,141,195,203],"academic":[10],"consist":[12],"of":[13,95,111,116,156,165,177,183],"nodes":[14,211],"with":[15,89,113,179],"textual":[16,134],"features":[17],"linked":[18],"by":[19,130,146],"various":[20],"relations.":[21],"Traditional":[22],"graph":[23,37,49,81],"machine":[24],"learning":[25],"models,":[26],"such":[27],"as":[28],"Graph":[29],"Neural":[30],"Networks":[31],"(GNNs),":[32],"excel":[33],"encoding":[35,80],"the":[36,67,109,114,132,153,157,162,173,180],"structural":[38,181],"information,":[39],"but":[40,71,159],"have":[41],"limited":[42],"capability":[43],"handling":[45],"rich":[46],"text":[47,59,68,91,121,144,158,174],"on":[48,201,227],"nodes.":[50,97],"Large":[51],"Language":[52],"Models":[53],"(LLMs),":[54],"noted":[55],"for":[56,65,79,198,210],"their":[57,77,84],"superior":[58],"understanding":[60],"abilities,":[61],"offer":[62],"a":[63,104,123,127,137,213,217,222],"solution":[64],"processing":[66,175],"graphs":[70],"face":[72],"integration":[73],"challenges":[74,164],"due":[75],"to":[76,107],"limitation":[78],"structures":[82],"computational":[85,163],"complexities":[86,182],"when":[87],"dealing":[88],"extensive":[90,133],"large":[93],"neighborhoods":[94],"interconnected":[96],"This":[98],"paper":[99],"introduces":[100],"``Hierarchical":[101],"Compression''":[102],"(HiCom),":[103],"novel":[105],"method":[106],"align":[108],"capabilities":[110],"LLMs":[112,178],"structure":[115],"text-rich":[117,184],"graphs.":[118,185,205],"HiCom":[119,149,190,206],"processes":[120],"node's":[124],"neighborhood":[125],"structured":[128],"manner":[129],"organizing":[131],"information":[135],"into":[136],"more":[138,232],"manageable":[139],"hierarchy":[140],"compressing":[142],"node":[143,199],"step":[145],"step.":[147],"Therefore,":[148],"not":[150],"only":[151],"preserves":[152],"contextual":[154],"richness":[155],"also":[160],"addresses":[161],"LLMs,":[166],"which":[167],"presents":[168],"an":[169],"advancement":[170],"integrating":[172],"power":[176],"Empirical":[186],"results":[187],"show":[188],"that":[189],"can":[191],"outperform":[192],"both":[193],"GNNs":[194],"LLM":[196,235],"backbones":[197],"classification":[200],"citation":[204],"is":[207],"especially":[208],"effective":[209],"from":[212],"dense":[214],"region":[215],"graph,":[218],"where":[219],"it":[220],"achieves":[221],"3.48%":[223],"average":[224],"performance":[225],"improvement":[226],"five":[228],"datasets":[229],"while":[230],"being":[231],"efficient":[233],"than":[234],"backbones.":[236]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}