Large-scale robust transductive support vector machines

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00311979" target="_blank" >RIV/68407700:21230/17:00311979 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.sciencedirect.com/science/article/pii/S0925231217300292" target="_blank" >http://www.sciencedirect.com/science/article/pii/S0925231217300292</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.neucom.2017.01.012" target="_blank" >10.1016/j.neucom.2017.01.012</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Large-scale robust transductive support vector machines

Popis výsledku v původním jazyce

In this paper, we propose a robust and fast transductive support vector machine (RTSVM) classifier that can be applied to large-scale data. To this end, we use the robust Ramp loss instead of Hinge loss for labeled data samples. The resulting optimization problem is non-convex but it can be decomposed to a convex and concave parts. Therefore, the optimization is accomplished iteratively by solving a sequence of convex problems known as concave-convex procedure. Stochastic gradient (SG) is used to solve the convex problem at each iteration, thus the proposed method scales well with large training set size for the linear case (to the best of our knowledge, it is the second transductive classification method that is practical for more than a million data). To extend the proposed method to the nonlinear case, we proposed two alternatives where one uses the primal optimization problem and the other uses the dual. But in contrast to the linear case, both alternatives do not scale well with large-scale data. Experimental results show that the proposed method achieves comparable results to other related transductive SVM methods, but it is faster than other transductive learning methods and it is more robust to the noisy data.

Název v anglickém jazyce

Large-scale robust transductive support vector machines

Popis výsledku anglicky

In this paper, we propose a robust and fast transductive support vector machine (RTSVM) classifier that can be applied to large-scale data. To this end, we use the robust Ramp loss instead of Hinge loss for labeled data samples. The resulting optimization problem is non-convex but it can be decomposed to a convex and concave parts. Therefore, the optimization is accomplished iteratively by solving a sequence of convex problems known as concave-convex procedure. Stochastic gradient (SG) is used to solve the convex problem at each iteration, thus the proposed method scales well with large training set size for the linear case (to the best of our knowledge, it is the second transductive classification method that is practical for more than a million data). To extend the proposed method to the nonlinear case, we proposed two alternatives where one uses the primal optimization problem and the other uses the dual. But in contrast to the linear case, both alternatives do not scale well with large-scale data. Experimental results show that the proposed method achieves comparable results to other related transductive SVM methods, but it is faster than other transductive learning methods and it is more robust to the noisy data.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LL1303" target="_blank" >LL1303: Vyhledávání vizuálních kategorií ve velkém množství obrázků</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neurocomputing

ISSN

0925-2312

e-ISSN

1872-8286

Svazek periodika

235

Číslo periodika v rámci svazku

April

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

199-209

Kód UT WoS článku

000395219700021

EID výsledku v databázi Scopus

2-s2.0-85009789274