Matches in SemOpenAlex for { <https://semopenalex.org/work/W2164179075> ?p ?o ?g. }
- W2164179075 endingPage "105" @default.
- W2164179075 startingPage "65" @default.
- W2164179075 abstract "Identifier attributes—very high-dimensional categorical attributes such as particular product ids or people's names—rarely are incorporated in statistical modeling. However, they can play an important role in relational modeling: it may be informative to have communicated with a particular set of people or to have purchased a particular set of products. A key limitation of existing relational modeling techniques is how they aggregate bags (multisets) of values from related entities. The aggregations used by existing methods are simple summaries of the distributions of features of related entities: e.g., MEAN, MODE, SUM, or COUNT. This paper's main contribution is the introduction of aggregation operators that capture more information about the value distributions, by storing meta-data about value distributions and referencing this meta-data when aggregating—for example by computing class-conditional distributional distances. Such aggregations are particularly important for aggregating values from high-dimensional categorical attributes, for which the simple aggregates provide little information. In the first half of the paper we provide general guidelines for designing aggregation operators, introduce the new aggregators in the context of the relational learning system ACORA (Automated Construction of Relational Attributes), and provide theoretical justification. We also conjecture special properties of identifier attributes, e.g., they proxy for unobserved attributes and for information deeper in the relationship network. In the second half of the paper we provide extensive empirical evidence that the distribution-based aggregators indeed do facilitate modeling with high-dimensional categorical attributes, and in support of the aforementioned conjectures." @default.
- W2164179075 created "2016-06-24" @default.
- W2164179075 creator A5003651471 @default.
- W2164179075 creator A5037283651 @default.
- W2164179075 date "2006-01-27" @default.
- W2164179075 modified "2023-09-26" @default.
- W2164179075 title "Distribution-based aggregation for relational learning with identifier attributes" @default.
- W2164179075 cites W1497163089 @default.
- W2164179075 cites W1498273559 @default.
- W2164179075 cites W1505528679 @default.
- W2164179075 cites W1517113043 @default.
- W2164179075 cites W1517567737 @default.
- W2164179075 cites W1518912663 @default.
- W2164179075 cites W1531743498 @default.
- W2164179075 cites W1545331097 @default.
- W2164179075 cites W1572684271 @default.
- W2164179075 cites W1738398458 @default.
- W2164179075 cites W1785889609 @default.
- W2164179075 cites W1987902506 @default.
- W2164179075 cites W2007497378 @default.
- W2164179075 cites W2023612196 @default.
- W2164179075 cites W2028137574 @default.
- W2164179075 cites W2033072307 @default.
- W2164179075 cites W2042123098 @default.
- W2164179075 cites W2073245587 @default.
- W2164179075 cites W2076008912 @default.
- W2164179075 cites W2078029048 @default.
- W2164179075 cites W2095263945 @default.
- W2164179075 cites W2107328434 @default.
- W2164179075 cites W2123827533 @default.
- W2164179075 cites W2131353734 @default.
- W2164179075 cites W2131479089 @default.
- W2164179075 cites W2132513611 @default.
- W2164179075 cites W2135863341 @default.
- W2164179075 cites W2155653793 @default.
- W2164179075 cites W2155800811 @default.
- W2164179075 cites W2162630660 @default.
- W2164179075 cites W4234473173 @default.
- W2164179075 doi "https://doi.org/10.1007/s10994-006-6064-1" @default.
- W2164179075 hasPublicationYear "2006" @default.
- W2164179075 type Work @default.
- W2164179075 sameAs 2164179075 @default.
- W2164179075 citedByCount "86" @default.
- W2164179075 countsByYear W21641790752012 @default.
- W2164179075 countsByYear W21641790752013 @default.
- W2164179075 countsByYear W21641790752014 @default.
- W2164179075 countsByYear W21641790752015 @default.
- W2164179075 countsByYear W21641790752016 @default.
- W2164179075 countsByYear W21641790752017 @default.
- W2164179075 countsByYear W21641790752018 @default.
- W2164179075 countsByYear W21641790752019 @default.
- W2164179075 countsByYear W21641790752020 @default.
- W2164179075 countsByYear W21641790752021 @default.
- W2164179075 countsByYear W21641790752022 @default.
- W2164179075 crossrefType "journal-article" @default.
- W2164179075 hasAuthorship W2164179075A5003651471 @default.
- W2164179075 hasAuthorship W2164179075A5037283651 @default.
- W2164179075 hasBestOaLocation W21641790751 @default.
- W2164179075 hasConcept C119857082 @default.
- W2164179075 hasConcept C124101348 @default.
- W2164179075 hasConcept C154504017 @default.
- W2164179075 hasConcept C159985019 @default.
- W2164179075 hasConcept C174348530 @default.
- W2164179075 hasConcept C177264268 @default.
- W2164179075 hasConcept C177877439 @default.
- W2164179075 hasConcept C192562407 @default.
- W2164179075 hasConcept C199360897 @default.
- W2164179075 hasConcept C31258907 @default.
- W2164179075 hasConcept C41008148 @default.
- W2164179075 hasConcept C4679612 @default.
- W2164179075 hasConcept C5274069 @default.
- W2164179075 hasConcept C5655090 @default.
- W2164179075 hasConceptScore W2164179075C119857082 @default.
- W2164179075 hasConceptScore W2164179075C124101348 @default.
- W2164179075 hasConceptScore W2164179075C154504017 @default.
- W2164179075 hasConceptScore W2164179075C159985019 @default.
- W2164179075 hasConceptScore W2164179075C174348530 @default.
- W2164179075 hasConceptScore W2164179075C177264268 @default.
- W2164179075 hasConceptScore W2164179075C177877439 @default.
- W2164179075 hasConceptScore W2164179075C192562407 @default.
- W2164179075 hasConceptScore W2164179075C199360897 @default.
- W2164179075 hasConceptScore W2164179075C31258907 @default.
- W2164179075 hasConceptScore W2164179075C41008148 @default.
- W2164179075 hasConceptScore W2164179075C4679612 @default.
- W2164179075 hasConceptScore W2164179075C5274069 @default.
- W2164179075 hasConceptScore W2164179075C5655090 @default.
- W2164179075 hasIssue "1-2" @default.
- W2164179075 hasLocation W21641790751 @default.
- W2164179075 hasLocation W21641790752 @default.
- W2164179075 hasLocation W21641790753 @default.
- W2164179075 hasOpenAccess W2164179075 @default.
- W2164179075 hasPrimaryLocation W21641790751 @default.
- W2164179075 hasRelatedWork W1498034582 @default.
- W2164179075 hasRelatedWork W1542469860 @default.
- W2164179075 hasRelatedWork W1982724950 @default.
- W2164179075 hasRelatedWork W2002046668 @default.
- W2164179075 hasRelatedWork W2187085270 @default.
- W2164179075 hasRelatedWork W3089218368 @default.