Co-Training for Domain Adaptation

By Minmin Chen, Kilian Q. Weinberger, John Blitzer. 2011

432 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

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 Comprehensive Survey on Transfer Learning (2019, methodology): “By the way, there are some other methods of providing pseudo labels such as co-training [71], [72] and tri-training [73], [74].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “uxiliary intermediate multi-view domain [104, 106, 103, 101, 107, 109]. Hence, HDA/HTL can strongly beneﬁt from multi-view learning techniques such as canonical correlation analysis [93], co-training [265], spectral embedding [116] and multiple kernel learning [114]. Similarly to HDA/HTL relying on ”
Demographic Factors Improve Classification Performance (2015, background): “We ﬁnd that demographic-aware models consistently outperform their agnostic counterparts in all tasks.”
Tagging Performance Correlates with Author Age (2015, background): “Selection biases are often thought of in terms of textual domains, motivating work in domain adaptation of NLP models (Daume III and Marcu, 2006; Ben-David et al., 2007; Daume III, 2007; Dredze et al., 2007; Chen et al., 2009; Chen et al., 2011, inter alia).”
Transfer Feature Learning with Joint Distribution Adaptation (2013, background): “According to the literature survey [16], existing transfer learning methods can be roughly organized into two categories: instance reweighting [3, 4] and feature extraction.”
Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training (2019, background): “Several subsequent works have relaxed this assumption and shown co-training to be effective in much more general settings (Balcan et al., 2005; Chen et al., 2011; Collins and Singer, 1999; Clark et al., 2018).”
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).”
Angular Visual Hardness (2019, background): “, 2012), unsupervised domain adaptation (Chen et al., 2011) and weakly-supervised learning (Tang et al.”
Multi-view learning overview: Recent progress and new challenges (2017, background): “[61] presented a variant of cotraining for domain adaptation which connects source and target domains whose distributions can differ substantially.”
Domain Adaptation on the Statistical Manifold (2014, background): “Unsupervised domain adaptation techniques therefore emerged as a solution to this challenging scenario where no labeled data is available from the target domain [34, 5, 8, 27].”
Generalizing a Person Retrieval Model Hetero- and Homogeneously (2018, background): “In [16], the idea of co-training is applied to domain adaptation by gradually adding the target samples of high-conﬁdence predictions to the training set.”
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation (2013, methodology): “In contrast, when there is no labeled data from the target domain to help learning , the problem is called unsupervised domain adaptation (Blitzer et al., 2007; 2006; Gopalan et al., 2011; Gong et al., 2012; Chen et al., 2011).”
MetaReg: Towards Domain Generalization using Meta-Regularization (2018, methodology): “Other notable works include the use of Maximum Mean Discrepancy (MMD) [21], Generative Adversarial Networks (GAN) [25][26], co-training [4], etc.”
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation (2020, methodology): “SSL approaches such as self-training [2, 37, 49], co-training [5, 70] and GAN based methods [11,32] have been widely applied to UDA [9,14,24,55,61,72,73], and vice versa.”
An introduction to domain adaptation and transfer learning (2018, methodology): “Later approaches are more nonlinear through the use of kernelization or by employing ”co-training” approaches [40,136].”
Unsupervised Domain Adaptation by Domain Invariant Projection (2013, background): “To address this issue, unsupervised domain adaptation approaches that rely on purely unsupervised target data have been proposed [28, 7, 8].”