Domain adaptation–can quantity compensate for quality?

By Shai Ben-David, Ruth Urner. 2013

75 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 Artificial Intelligence

Citations in the corpus

Multi-Source Domain Adaptation: A Causal View (2015, background): “|X remain the same, i.e., the covariate shift situation; see, e.g., (Shimodaira 2000; Huang et al. 2007; Sugiyama et al. 2008; Ben-David, Shalev-Shwartz, and Urner 2012).”
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (2019, background): “Existing theories without assumptions of contained support (Ben-David et al., 2007, 2010a; Ben-David & Urner, 2014; Mansour et al., 2009; Cortes & Mohri, 2011) do not exhibit this property since (i) when applied to the input space, their results are not concerned with domain-adversarial learning as…”
A DIRT-T Approach to Unsupervised Domain Adaptation (2018, background): “Indeed, Ben-David & Urner (2014) formalized the cluster assumption through the lens of probabilistic Lipschitzness and proposed a nearest-neighbors model for domain adaptation.”
Unsupervised Domain Adaptive Re-Identification: Theory and Practice (2018, methodology): “It is assumed that the source domain and the target domain share a same label space in [3].”
Unsupervised Visual Domain Adaptation Using Subspace Alignment (2013, methodology): “Based on the recommendations of [2], we propose a discrepancy measure to estimate the local density of a target point w.”
Joint distribution optimal transportation for domain adaptation (2017, methodology): “To provide some guarantees on our method, we consider an adaptation of the notion probabilistic Lipschitzness introduced in [21, 22] which assumes that two close instances must have the same labels with high probability.”
On Localized Discrepancy for Domain Adaptation (2020, background): “A series of works Ben-David and Urner (2014); Scott (2018); Martinet and Kpotufe (2018) provide theoretical results for domain adaptation with non-parametric models.”
A New PAC-Bayesian Perspective on Domain Adaptation (2015, background): “The weight ratio (Ben-David et al., 2012) of source and target domains, with respect to a collection of input space subsets B ✓ 2 , is given by When B ( , T ) is bounded away from 0 , adaptation should be achievable under covariate shift.”
Support and Invertibility in Domain-Invariant Representations (2019, background): “Johansson, David Sontag, Rajesh Ranganath Theorem 1 (Adaptation bound by Ben-David et al. (2010a)).”
Unsupervised Domain Adaptation with a Relaxed Covariate Shift Assumption (2017, background): “Covariate shift states that the conditional labeling distributions of both the source and target domains are the same, while their respective marginal data distributions can be different (Storkey and Sugiyama 2006; Ben-David and Urner 2012; 2014).”
Extracting Relationships by Multi-Domain Matching (2018, background): “At test time, only the domains most relevant to the target are used [5, 32].”