Large Scale Transductive SVMs

By Ronan Collobert, Fabian H Sinz, Jason Aaron Edward Weston, L. Eon Bottou. 2006

535 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

Citations in the corpus

Adversarial Training Methods for Semi-Supervised Text Classification (2016, methodology): “Adversarial and virtual adversarial training resemble some semi-supervised or transductive SVM approaches (Joachims, 1999; Chapelle & Zien, 2005; Collobert et al., 2006; Belkin et al., 2006) in that both families of methods push the decision boundary far from training examples (or in the case of…”
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning (2017, methodology): “N l = 100 N l = 1000 TSVM [5] 16.81 5.38 Pseudo Ensembles Agreement (PEA) [3] 5.21 2.87 Deep Generative Model [19] 3.33 2.59 CatGAN [33] 1.91 1.73 Ladder Networks [30] 1.06 0.84 GAN with feature matching [32] 0.93 For the experiments on SVHN and CIFAR-10, we used two types of CNNs (Conv-Small and…”
Deep learning via semi-supervised embedding (2008, methodology): “The first three are small scale datasets used in the same experimental setup as found in [9, 24, 10].”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “, [140], [150]–[152].”
Large Graph Construction for Scalable Semi-Supervised Learning (2010, background): “Among various versions of TSVM, CCCP-TSVM (Collobert et al., 2006) has the lowest complexity, but it scales as at least O(n(2)) so it is still difficult to scale up.”
Multi-Label Classification with Unlabeled Data: An Inductive Approach (2013, methodology): “In this paper, the ConCave Convex Procedure( CCCP ) method [Collobert et al. (2006)][Chapelle et al. (2008)] is applied to solve the non-convex optimization problem.”
Support Vector Machine Solvers (2007, methodology): “Three additional ideas define the modern SVMs.”
EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks (2020, methodology): “Considering that the subject-independent emotion recognition task can be seen as a cross-domain emotion recognition problem, we adopt several popular cross-domain recognition methods, including transfer component analysis (TCA) [57], KPCA [58], transductive SVM (T-SVM) [59] and”
Supervised classification and mathematical optimization (2013, unknown): “In [65], a global optimization problem in”
Discriminative Semi-Supervised Feature Selection Via Manifold Regularization (2009, methodology): “The representative approaches in this category include tranductive support vector machine (SVM) and semi-supervised SVM [11], [12], [27], [54], [59], [60].”
Multiple instance learning for sparse positive bags (2007, methodology): “…the optimization formulation with a constraint |w f(x)+b|=1-.x on the value of the decision function for every unlabeled instance x. Recently, Collobert et al. (2006) have given an approximation method for solving the resulting non-convex optimization problem, in which the objective…”
Semisupervised Neural Networks for Efficient Hyperspectral Image Classification (2010, background): “Finally, the concave convex procedure-TSVM scales better—almost quadratically—but it is still impractical for more than 200 000 samples [29].”
Learning with Augmented Class by Exploiting Unlabeled Data (2014, methodology): “From the derivation in (Collobert et al. 2006), the symmetric hinge loss can be approximated by Here R s ( z ) = min(1 − s, max(0 , 1 − z )) is the ramp loss with a hyper-parameter s ∈ ( − 1 , 0] .”
Semi-Supervised Learning via Generalized Maximum Entropy (2010, methodology): “Moreover, our approach provides an intuitive way of imposing balanced label proportions on labeled and unlabeled samples, which has been successfully used in the earlier semi-supervised learning literature (Collobert et al., 2006; Chapelle & Zien, 2005; Karlen et al., 2008).”
Selective Transfer Machine for Personalized Facial Action Unit Detection (2013, methodology): “T-SVM is formulated as integer programming, which is difﬁcult to optimize and scale to large problems.”
A Proof of Convergence of the Concave-Convex Procedure Using Zangwill's Theory (2012, background): “However, the assumptions on u and v as mentioned in theorem 3 are usually satisfied in machine learning applications, the examples of which include sparse principal component analysis (Sriperumbudur et al., 2007), feature selection in SVMs (Neumann et al., 2005), and transductive SVMs (Collobert et ”