Domain Adaptation with Coupled Subspaces

By John Blitzer, Sham M. Kakade, Dean Phillips Foster. 2011

135 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.

Citations in the corpus

Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “ that arise in different application scenarios (see a few examples in Figure 1). Examples include DA and TL solutions for named entity recognition and opinion extraction across different text corpora [59, 161, 15, 276], multilanguage text classiﬁcation [167, 275, 274], sentiment analysis [35, 100], ”
Generalized Transfer Subspace Learning Through Low-Rank Constraint (2014, background): “Transductive transfer learning (Arnold et al. 2007; Dai et al. 2007a,b), and specifically, domain adaptation (Daumé III and Marcu 2006; Blitzer et al. 2006, 2011; Daumé 2007; Sun et al. 2011; Glorot et al. 2011; Chen et al. 2011; Lopez-Paz et al. 2012; Zhang et al. 2012) transforms the source…”
Unsupervised Visual Domain Adaptation Using Subspace Alignment (2013, methodology): “We project the source data onto the source subspace and the target data onto the target subspace in contrast to methods that project source data to the target subspace or target data to the source subspace such as [3].”
Co-Training for Domain Adaptation (2011, background): “[5], learns a shared representation under which the source and target distributions are closer than under the ambient feature space [28].”
Robustness to Spurious Correlations via Human Annotations (2020, background): “Existing approaches such as distributional robustness (Ben-Tal et al., 2013; Lam & Zhou, 2015) and domain adaptation (Mansour et al., 2009b; Blitzer et al., 2011; Gong et al., 2013) require either a priori specifying the distribution shifts, or sampling from the target test distributions.”
Cross Language Text Classification via Subspace Co-regularized Multi-view Learning (2012, background): “…generalizable features from the two domains, including structural correspondence learning (Blitzer et al., 2006), coupled subspace learning (Blitzer et al., 2011), and feature augmentation methods, easyadapt (EA) (Daum´e III, 2007) and its co-regularization based semi-supervised extension…”
Distributionally Robust Language Modeling (2019, methodology): “Daume III, 2007; Ben-David et al., 2010; Blitzer et al., 2011; Pryzant et al., 2017) or domain-invariant features (Ganin and Lempitsky, 2015; Tzeng et al., 2014).”
Multi-view Domain Generalization for Visual Recognition (2015, methodology): “As discussed in Section 1, several domain adaptation methods [3, 41, 39] were recently proposed under the multi-view setting.”
Transfer Knowledge between Cities (2016, background): “Blitzer et. al [2] pointed out the limitations of parameter and instance transfer in dealing with a target domain whose distribution distinctly di ﬀ ers from a source’s.”
Unsupervised Risk Estimation with only Structural Assumptions (2016, background): “Our work does not strictly generalize the work above, as for instance Kakade & Foster (2007) and Blitzer et al. (2011) assume low regret but not independence, and consider regression rather than classification.”
Unsupervised Domain Adaptation by Domain Invariant Projection (2013, methodology): “In particular, in [4], coupled subspaces are learned using Canonical Correlation Analysis (CCA).”
A Review of Domain Adaptation without Target Labels (2019, background): “Thus, by augmenting the bag-of-words encoding with pivot words and learning correspondences, it is possible to construct features common to both domains [13], [171].”
Joint cross-domain classification and subspace learning for unsupervised adaptation (2014, methodology): “We present an algorithm that learns jointly both a low dimensional representation and a reliable classifier by optimizing a trade-off between the sourcetarget similarity and the source training error.”
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation (2013, background): “One extensively studied paradigm is to assume that there is a domaininvariant feature space (Blitzer et al., 2007; 2006; Gopalan et al., 2011; Blitzer et al., 2011; Chen et al., 2011; Ben-David et al., 2007; 2010; Pan et al., 2009).”
An introduction to domain adaptation and transfer learning (2018, background): “Adaptation consists of augmenting the bag-of-words encoding with pivot words, learning correspondences and training on the augmented feature space [27,26,40,136].”