Multitask algorithms typically use task similarity information as a bias to speed up and improve the performance of learning processes. Tasks are learned jointly, sharing information across them, in order to construct models more accurate than those learned separately over single tasks. In this contribution, we present the first multitask model, to our knowledge, based on Hopfield Networks (HNs), named HoMTask. We show that by appropriately building a unique HN embedding all tasks, amore robust and effective classification model can be learned. HoMTask is a transductive semi-supervised parametric HN, that minimizes an energy function extended to all nodes and to all tasks under study. We provide theoretical evidence that the optimal parameters automatically estimated by HoMTask make coherent the model itself with the prior knowledge (connection weights and node labels). The convergence properties of HNs are preserved, and the fixed point reached by the network dynamics gives rise to the prediction of unlabeled nodes. The proposed model improves the classification abilities of singletask HNs on a preliminary benchmark comparison, and achieves competitive performance with state-of-the-art semi-supervised graph-based algorithms.

Multitask Hopfield Networks / M. Frasca, G. Grossi, G. Valentini (LECTURE NOTES IN COMPUTER SCIENCE). - In: Machine Learning and Knowledge Discovery in Databases / [a cura di] U. Brefeld, E. Fromont, A. Hotho, A. Knobbe, M. Maathuis, C. Robardet. - [s.l] : Springer, 2020. - ISBN 9783030461461. - pp. 349-365 (( convegno European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases tenutosi a Würzburg nel 2019.

Multitask Hopfield Networks

M. Frasca
;
G. Grossi;G. Valentini
2020

Abstract

Multitask algorithms typically use task similarity information as a bias to speed up and improve the performance of learning processes. Tasks are learned jointly, sharing information across them, in order to construct models more accurate than those learned separately over single tasks. In this contribution, we present the first multitask model, to our knowledge, based on Hopfield Networks (HNs), named HoMTask. We show that by appropriately building a unique HN embedding all tasks, amore robust and effective classification model can be learned. HoMTask is a transductive semi-supervised parametric HN, that minimizes an energy function extended to all nodes and to all tasks under study. We provide theoretical evidence that the optimal parameters automatically estimated by HoMTask make coherent the model itself with the prior knowledge (connection weights and node labels). The convergence properties of HNs are preserved, and the fixed point reached by the network dynamics gives rise to the prediction of unlabeled nodes. The proposed model improves the classification abilities of singletask HNs on a preliminary benchmark comparison, and achieves competitive performance with state-of-the-art semi-supervised graph-based algorithms.
Multitask Hopfield networks; multitask learning
Settore INF/01 - Informatica
2020
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Frasca_ecml19v2.pdf

accesso riservato

Descrizione: Articolo principale
Tipologia: Pre-print (manoscritto inviato all'editore)
Dimensione 576.02 kB
Formato Adobe PDF
576.02 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
1904.05098.pdf

accesso aperto

Tipologia: Pre-print (manoscritto inviato all'editore)
Dimensione 656.12 kB
Formato Adobe PDF
656.12 kB Adobe PDF Visualizza/Apri
Frasca2020_Chapter_MultitaskHopfieldNetworks.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 595.62 kB
Formato Adobe PDF
595.62 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/713025
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact