Type extension trees: a unified framework for relational feature construction

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstrakt

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.
OriginalsprogEngelsk
TitelProceedings of the International Workshop on Mining and Learning with Graphs : in conjunction with ECML/PKDD 2006
Antal sider12
Publikationsdato2006
Sider49-60
StatusUdgivet - 2006
BegivenhedInternational Workshop on Mining and Learning with Graphs - Berlin, Tyskland
Varighed: 19 maj 2010 → …

Konference

KonferenceInternational Workshop on Mining and Learning with Graphs
LandTyskland
ByBerlin
Periode19/05/2010 → …

Fingeraftryk Dyk ned i forskningsemnerne om 'Type extension trees: a unified framework for relational feature construction'. Sammen danner de et unikt fingeraftryk.

Citationsformater