{"id":"https://openalex.org/W2140127353","doi":null,"title":"Avoiding bias when aggregating relational data with degree disparity","display_name":"Avoiding bias when aggregating relational data with degree disparity","publication_year":2003,"publication_date":"2003-08-21","ids":{"openalex":"https://openalex.org/W2140127353","mag":"2140127353"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.3772","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.3772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/conferences/icml2003/papers/288.pdf","raw_type":"text"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5006681132","display_name":"David D. Jensen","orcid":"https://orcid.org/0000-0001-5653-3349","observed_orcids":["https://orcid.org/0000-0001-5653-3349"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jensen","raw_affiliation_strings":["Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-5653-3349","affiliations":[{"raw_affiliation_string":"Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064439579","display_name":"Jennifer Neville","orcid":"https://orcid.org/0000-0001-8108-4899","observed_orcids":["https://orcid.org/0000-0001-8108-4899","https://orcid.org/0009-0007-1157-018X"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Neville","raw_affiliation_strings":["Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-8108-4899","affiliations":[{"raw_affiliation_string":"Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020275137","display_name":"Michael Hay","orcid":"https://orcid.org/0000-0001-9085-893X","observed_orcids":["https://orcid.org/0000-0001-9085-893X"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Hay","raw_affiliation_strings":["Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Discovery Laboratory, Computer Science Dept., Univ. of Massachusetts Amherst, Amherst, MA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":3.5324,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93651498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.36010000109672546,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.36010000109672546,"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"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.09009999781847,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.08780000358819962,"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/relational-data","display_name":"relational data","score":0.6520000100135803},{"id":"https://openalex.org/keywords/aggregation-bias","display_name":"aggregation bias","score":0.7369999885559082},{"id":"https://openalex.org/keywords/relational-learning","display_name":"relational learning","score":0.8339999914169312}],"concepts":[{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.7891830801963806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6131295561790466},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4871368110179901},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.48301494121551514},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.4620288014411926},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.45369720458984375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38717883825302124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36818671226501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3535723090171814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3035908341407776},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.3772","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.3772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/conferences/icml2003/papers/288.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.5613","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.5613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kdl.cs.umass.edu/~jneville/papers/jensen-etal-TR-03-14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.9125","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.9125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kdl.cs.umass.edu/papers/jensen-et-al-icml2003.pdf","raw_type":"text"},{"id":"mag:2140127353","doi":null,"is_oa":false,"landing_page_url":"http://cs.colgate.edu/~mhay/assets/publications/jensen2003avoiding.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W150885707","https://openalex.org/W1498800329","https://openalex.org/W1513527572","https://openalex.org/W1526304375","https://openalex.org/W1572684271","https://openalex.org/W1593468624","https://openalex.org/W1608683810","https://openalex.org/W1608864735","https://openalex.org/W1666347389","https://openalex.org/W1700914952","https://openalex.org/W2028137574","https://openalex.org/W2120959311","https://openalex.org/W2123504579","https://openalex.org/W2126185296","https://openalex.org/W2127743671","https://openalex.org/W2135863341","https://openalex.org/W2314731117","https://openalex.org/W2612575796"],"related_works":["https://openalex.org/W2521167396","https://openalex.org/W93424371","https://openalex.org/W2905002016","https://openalex.org/W128978003","https://openalex.org/W3028284342","https://openalex.org/W3175697631","https://openalex.org/W4251553022","https://openalex.org/W7096386478","https://openalex.org/W3143082381","https://openalex.org/W3135881404"],"abstract_inverted_index":{"A":[0],"common":[1],"characteristic":[2],"of":[3,21,29,33,75,92,99],"relational":[4,9,47],"data":[5],"sets":[6],"leads":[7],"many":[8,46],"learning":[10,48],"algorithms":[11,49],"to":[12],"discover":[13],"misleading":[14,61],"correlations.":[15],"This":[16],"characteristic\u2014degree":[17],"disparity\u2014occurs":[18],"when":[19],"entities":[20,32],"one":[22],"class":[23],"participate":[24],"in":[25,45,60,66,96],"systematically":[26],"higher":[27],"numbers":[28],"relations":[30],"than":[31],"another":[34],"class.":[35],"In":[36],"such":[37],"cases,":[38],"the":[39,90,97],"aggregation":[40,94],"functions":[41,95],"that":[42],"are":[43],"used":[44],"(e.g.,":[50],"AVG,":[51],"MODE,":[52],"SUM,":[53],"EXISTS,":[54],"COUNT,":[55],"MAX,":[56],"MIN)":[57],"will":[58],"result":[59],"correlations":[62],"and":[63,77],"added":[64],"complexity":[65],"models.":[67],"We":[68,79],"examine":[69],"this":[70],"problem":[71],"through":[72],"a":[73],"combination":[74],"simulations":[76],"experiments.":[78],"show":[80],"how":[81],"two":[82],"novel":[83],"significance":[84],"testing":[85],"procedures":[86],"can":[87],"adjust":[88],"for":[89],"effects":[91],"using":[93],"presence":[98],"degree":[100],"disparity.":[101],"1.":[102]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}