Flexible Transfer Learning under Support and Model Shift

By Xuezhi Wang, Jeff Schneider. 2014

98 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

Multi-Adversarial Domain Adaptation (2018, background): “Transfer learning (Pan and Yang 2010) bridges different domains or tasks to mitigate the burden of manual labeling for machine learning (Pan et al. 2011; Duan, Tsang, and Xu 2012; Zhang et al. 2013; Wang and Schneider 2014), computer vision (Saenko et al.”
Deep Transfer Learning with Joint Adaptation Networks (2016, background): “Another line of work [4, 5, 6] gives principled approaches to correcting both target and conditional shifts based on the theory of kernel embedding of conditional distributions [11], which is a remarkable step towards full-transfer of joint distributions.”
Partial Adversarial Domain Adaptation (2018, background): “Domain adaptation [1] bridges different domains following different distributions to mitigate the burden of manual labeling for machine learning [13,14,15,16], computer vision [17,18,19] and natural language processing [20].”
Fair Transfer Learning with Missing Protected Attributes (2019, background): “Unsupervised domain adaptation to account for covariate shift can be achieved by forms of transfer learning (Gong et al. 2012; Wang and Schneider 2014).”
Efficient Meta Learning via Minibatch Proximal Update (2019, background): “Minibatch proximal learning is also identical in principle to biased regularized hypothesis transfer learning, which has been explored experimentally with success in many applications [31, 32, 33] and theoretically with rigourous guarantees [34, 35].”
Neurosymbolic Programming (2021, background): “, efficiently generalizing to new domains) (Wang and Schneider, 2014), discussed further in the next section.”
Multi-Layer domain adaptation method for rolling bearing fault diagnosis (2019, background): “In [35–37], shallow domain-invariant features are learned by minimizing the discrepancy.”
Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks (2019, background): “In [13]–[15], shallow domaininvariant features are learned by optimizing distribution.”
I Have Seen Enough: Transferring Parts Across Categories (2016, background): “Only very few works have jointly looked at transfer learning and active learning [3, 37, 42, 58, 59] 1The dataset can be downloaded at www.”
Universal Source-Free Domain Adaptation (2020, background): “The cluster of prior closed-set DA works focuses on minimizing the domain gap at the latent space either by minimizing well-defined statistical distance functions [49, 8, 55, 37] or by formalizing it as an adversarial distribution matching problem [46, 17, 27, 16, 15] inspired from the Generative Ad”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “A rich line of prior works have focused on learning shallow features by jointly minimizing a distance metric of domain discrepancy (Pan et al., 2011; Long et al., 2013; Baktashmotlagh et al., 2013; Gong et al., 2013; Zhang et al., 2013; Ghifary et al., 2014; Wang & Schneider, 2014).”
Learning to Transfer Examples for Partial Domain Adaptation (2019, background): “Domain Adaptation Domain adaptation, a special scenario of transfer learning [29], bridges domains of different distributions to mitigate the burden of annotating target data for machine learning [28, 9, 44, 41], computer vision [32, 12, 16] and natural language processing [7].”
Understanding How Feature Structure Transfers in Transfer Learning (2017, background): “, 2006], model shift (Py|x differs across domains) [Wang and Schneider, 2014], target shift (Py differs across domains) [Zhang et al.”