We study an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be useful in various scenarios, such as graph classification, image classification and translation-invariant pooling in convolutional neural network. In order to learn multi-multi instance data, we introduce a special neural network layer, called bag-layer, whose units aggregate sets of inputs of arbitrary size. We prove that the associated class of functions contains all Boolean functions over sets of sets of instances. We present empirical results on semi-synthetic data showing that such class of functions can be actually learned from data. We also present experiments on citation graphs datasets where our model obtains competitive results.

A network architecture for multi-multi-instance learning / Alessandro Tibo, Paolo Frasconi, Manfred Jaeger. - ELETTRONICO. - (2017), pp. 737-752. (Intervento presentato al convegno ECML).

A network architecture for multi-multi-instance learning

Alessandro Tibo;Paolo Frasconi;
2017

Abstract

We study an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be useful in various scenarios, such as graph classification, image classification and translation-invariant pooling in convolutional neural network. In order to learn multi-multi instance data, we introduce a special neural network layer, called bag-layer, whose units aggregate sets of inputs of arbitrary size. We prove that the associated class of functions contains all Boolean functions over sets of sets of instances. We present empirical results on semi-synthetic data showing that such class of functions can be actually learned from data. We also present experiments on citation graphs datasets where our model obtains competitive results.
2017
Joint European Conference on Machine Learning and Knowledge Discovery in Databases
ECML
Alessandro Tibo, Paolo Frasconi, Manfred Jaeger
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/2158/1148991
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 3
social impact