In Kernel-based Learning the targeted phenomenon is summarized by a set of explanatory examples derived from the training set. When the model size grows with the complexity of the task, such approaches are so computationally demanding that the adoption of comprehensive models is not always viable. In this paper, a general framework aimed at minimizing this problem is proposed: multiple classifiers are stratified and dynamically invoked according to increasing levels of complexity corresponding to incrementally more expressive representation spaces. Computationally expensive inferences are thus adopted only when the classification at lower levels is too uncertain over an individual instance. The application of complex functions is thus avoided where possible, with a significant reduction of the overall costs. The proposed strategy has been integrated within two well-known algorithms: Support Vector Machines and Passive-Aggressive Online classifier. A significant cost reduction (up to 90%), with a negligible performance drop, is observed against two Natural Language Processing tasks, i.e. Question Classification and Sentiment Analysis in Twitter.

Filice, S., Croce, D., & Basili, R. (2015). A stratified strategy for efficient kernel-based learning. In Proceedings of the National Conference on Artificial Intelligence (pp.2239-2245). AI Access Foundation.

A stratified strategy for efficient kernel-based learning

CROCE, DANILO;BASILI, ROBERTO
2015-01-01

Abstract

In Kernel-based Learning the targeted phenomenon is summarized by a set of explanatory examples derived from the training set. When the model size grows with the complexity of the task, such approaches are so computationally demanding that the adoption of comprehensive models is not always viable. In this paper, a general framework aimed at minimizing this problem is proposed: multiple classifiers are stratified and dynamically invoked according to increasing levels of complexity corresponding to incrementally more expressive representation spaces. Computationally expensive inferences are thus adopted only when the classification at lower levels is too uncertain over an individual instance. The application of complex functions is thus avoided where possible, with a significant reduction of the overall costs. The proposed strategy has been integrated within two well-known algorithms: Support Vector Machines and Passive-Aggressive Online classifier. A significant cost reduction (up to 90%), with a negligible performance drop, is observed against two Natural Language Processing tasks, i.e. Question Classification and Sentiment Analysis in Twitter.
29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
usa
2015
AI Journal
Rilevanza internazionale
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
English
Software; Artificial Intelligence
Intervento a convegno
Filice, S., Croce, D., & Basili, R. (2015). A stratified strategy for efficient kernel-based learning. In Proceedings of the National Conference on Artificial Intelligence (pp.2239-2245). AI Access Foundation.
Filice, S; Croce, D; Basili, R
File in questo prodotto:
File Dimensione Formato  
AAAI_cameraReady_v0.8.pdf

non disponibili

Licenza: Copyright dell'editore
Dimensione 349.67 kB
Formato Adobe PDF
349.67 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/2108/157909
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact