Type Extension Trees are a powerful representation language for “count-of-count” features characterizing the combinatorial structure of neighborhoods of entities in relational domains. In this paper we present a learning algorithm for Type Extension Trees (TET) that discovers informative count-of-count features in the supervised learning setting. Experiments on bibliographic data show that TET-learning is able to discover the count-of-count feature underlying the definition of the h-index, and the inverse document frequency feature commonly used in information retrieval. We also introduce a metric on TET feature values. This metric is defined as a recursive application of the Wasserstein–Kantorovich metric. Experiments with a k-NN classifier show that exploiting the recursive count-of-count statistics encoded in TET values improves classification accuracy over alternative methods based on simple count statistics.

Type Extension Trees for feature construction and learning in relational domains / Manfred Jaeger;Marco Lippi;Andrea Passerini;Paolo Frasconi. - In: ARTIFICIAL INTELLIGENCE. - ISSN 0004-3702. - STAMPA. - 204:(2013), pp. 30-55. [10.1016/j.artint.2013.08.002]

Type Extension Trees for feature construction and learning in relational domains

Marco Lippi;FRASCONI, PAOLO
2013

Abstract

Type Extension Trees are a powerful representation language for “count-of-count” features characterizing the combinatorial structure of neighborhoods of entities in relational domains. In this paper we present a learning algorithm for Type Extension Trees (TET) that discovers informative count-of-count features in the supervised learning setting. Experiments on bibliographic data show that TET-learning is able to discover the count-of-count feature underlying the definition of the h-index, and the inverse document frequency feature commonly used in information retrieval. We also introduce a metric on TET feature values. This metric is defined as a recursive application of the Wasserstein–Kantorovich metric. Experiments with a k-NN classifier show that exploiting the recursive count-of-count statistics encoded in TET values improves classification accuracy over alternative methods based on simple count statistics.
2013
204
30
55
Manfred Jaeger;Marco Lippi;Andrea Passerini;Paolo Frasconi
File in questo prodotto:
File Dimensione Formato  
AIJ13-TET.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 730.04 kB
Formato Adobe PDF
730.04 kB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/823154
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact