Automatic Feature Decomposition for Single View Co-training

By Minmin Chen, Kilian Q. Weinberger, Yixin Chen. 2011

105 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.

1. Dacheng Tao
2. Yoshua Bengio
3. Quoc V. Le
4. Yi Yang
5. Sebastian Ruder
6. Zhe Gan
7. Percy Liang
8. Mohit Bansal

Citations in the corpus

• Marginalized Denoising Autoencoders for Domain Adaptation (2012, methodology): “Instead of learning a single mapping W ∈ R d × ( d +1) to reconstruct all corrupted features, we learn multiple mappings but only reconstruct the r (cid:28) d (Blitzer et. al., 2007) CODA (Chen et. al., 2011) SDA (Glorot et. al., 2011) mSDA (l=5) most frequent features (here, r = 5000 ).”
• A Survey on Multi-view Learning (2013, methodology): “Chen et al. (2010) developed a statistical framework that learns a predictive subspace shared by multiple views based on a generic multi-view latent space Markov network. Quadrianto and Lampert (2011) studied the metric learning problem in cross-media retrieval tasks.”
• Dash: Semi-Supervised Learning with Dynamic Thresholding (2021, background): “…self-training [Yarowsky, 1995, Lee, 2013, Rosenberg et al., 2005, Sajjadi et al., 2016, Laine and Aila, 2017, Xie et al., 2020b] and co-training [Blum and Mitchell, 1998, Zhou and Li, 2005, Sindhwani and Rosenberg, 2008, Wang et al., 2008, Yu et al., 2008, Wang and Zhou, 2010, Chen et al., 2011].”
• Neural Structural Correspondence Learning for Domain Adaptation (2016, background): “…in the machine learning literature, including instance reweighting (Huang et al., 2007; Mansour et al., 2009), sub-sampling from both domains (Chen et al., 2011) and learning joint target and source feature representations (Blitzer et al., 2006; Daum´e III, 2007; Xue et al., 2008; Glorot et…”
• Co-Training for Domain Adaptation (2011, methodology): “Further, we introduce pseudo multi-view co-training [7, 10], which improves the rote-learning procedure by adding inputs with features that are still not used effectively by the current classifier.”
• Marginalized Denoising Auto-encoders for Nonlinear Representations (2014, background): “It is worth pointing out that this type of orthogonality regularization has been used in other settings of learning models with disjoint sets of features (Hwang et al., 2011; Zhou et al., 2011; Chen et al., 2011).”
• A survey on semi-supervised learning (2019, background): “Chen et al. (2011) attempted to alleviate the need for pre-defined disjoint feature sets by automatically splitting the feature set in each co-training iteration.”
• On Feature Normalization and Data Augmentation (2020, background): “For instance, one could factorize the hidden features, or learn decompositions (Chen et al., 2011).”
• Wasserstein Distance Guided Representation Learning for Domain Adaptation (2017, background): “2009), subsampling (Chen, Chen, and Weinberger 2011), feature mapping (Tzeng et al. 2014) and weight regularization (Rozantsev, Salzmann, and Fua 2016).”
• Pivot Based Language Modeling for Improved Neural Domain Adaptation (2018, methodology): “Several approaches to DA have been proposed, for example: instance reweighting (Huang et al., 2007; Mansour et al., 2009), sub-sampling from both domains (Chen et al., 2011) and learning joint target and source feature representations (DReL), the approach we take here.”
• Bi-Transferring Deep Neural Networks for Domain Adaptation (2016, background): “…2007; Blitzer et al., 2006; Blitzer et al., 2007; Daume III, 2007; Li and Zong, 2008; Li et al., 2009; Pan et al., 2010; Kumar et al., 2010; Glo-rot et al., 2011; Chen et al., 2011a; Chen et al., 2012; Li et al., 2012; Xia et al., 2013a; Li et al., 2013; Zhou et al., 2015a; Zhuang et al., 2015).”