Type extension trees: a unified framework for relational feature construction

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

We introduce type extension trees as a formal representation language for complex combinatorial features of relational data. Based on a very simple syntax this language provides a unified framework for expressing features as diverse as embedded
subgraphs on the one hand, and marginal counts of attribute values on the other. We show by various examples how many existing relational data mining techniques can be expressed as the problem of constructing a type extension tree and a discriminant
function.
Original languageEnglish
Title of host publicationProceedings of the International Workshop on Mining and Learning with Graphs : in conjunction with ECML/PKDD 2006
Number of pages12
Publication date2006
Pages49-60
Publication statusPublished - 2006
EventInternational Workshop on Mining and Learning with Graphs - Berlin, Germany
Duration: 19 May 2010 → …

Conference

ConferenceInternational Workshop on Mining and Learning with Graphs
CountryGermany
CityBerlin
Period19/05/2010 → …

    Fingerprint

Cite this

Jaeger, M. (2006). Type extension trees: a unified framework for relational feature construction. In Proceedings of the International Workshop on Mining and Learning with Graphs: in conjunction with ECML/PKDD 2006 (pp. 49-60)