Domain Adaptation with Multiple Sources

By Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh. 2008

589 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

A theory of learning from different domains (2010, background): “More recently, Mansour et al. (2009a, 2009b) introduced a theoretical model for the “multiple source adaptation problem.””
Advances and Open Problems in Federated Learning (2019, background): “Can we guarantee that the model hFL learned via federated learning is at least as accurate as hk when used for client k? Can we quantify how much improvement can be expected via federated leaning? And can we develop personalization strategies with theoretical guarantees that at least match the perfo”
Marginalized Denoising Autoencoders for Domain Adaptation (2012, methodology): “Recent work has investigated several techniques for alleviating the difference: instance reweighting (Huang et al., 2007; Mansour et al., 2009), sub-sampling from both domains (Chen et al., 2011b) and learning joint target and source feature representations (Blitzer et al., 2006; Glorot et al.,…”
Multiple-Source Adaptation with Domain Classifiers (2020, methodology): “…information available to the learner, the number of source domains, and the amount of labeled and unlabeled data available from the target domain [Mansour et al., 2008, 2009a, Hoffman et al., 2018, Pan and Yang, 2010, Muandet et al., 2013, Xu et al., 2014, Hoffman et al., 2012, Gong et al.,…”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, background): “It was shown by Mansour et al. (2009c) (see also Cortes and Mohri (2011)) that the discrepancy is the appropriate divergence between distributions in adaptation.”
Agnostic Federated Learning (2019, methodology): “In the multiple-source adaptation problem studied by Mansour, Mohri, and Rostamizadeh (2009c,a) and Hoffman, Mohri, and Zhang (2018), each domain k is deﬁned by the corresponding distribution D k and the learner has only access to a predictor h k for each domain and no access to labeled training…”
Algorithms and Theory for Multiple-Source Adaptation (2018, methodology): “These results generalize a previous lower bound of Mansour et al. (2008). Next, we show that the distribution-weighted combination rule is a suitable solution.”
Multi-Source Domain Adaptation: A Causal View (2015, methodology): “For the distribution weighted rule, the same coefﬁcient, 1 /n , was used in (Mansour, Mohri, and Rostamizadeh 2008) for all sources; here we denote this method by simple adapt .”
Domain Adaptation: Learning Bounds and Algorithms (2009, background): “A theoretical study of domain adaptation was presented by Mansour et al. (2009), where the analysis deals with the related but distinct case of adaptation with multiple sources, and where the target is a mixture of the source distributions.”
Moment Matching for Multi-Source Domain Adaptation (2018, background): “Originated from the early theoretical analysis [1, 28, 4], MSDA has many practical applications [45, 6].”
Domain Separation Networks (2016, background): “[18] extend the theory of [4] to handle the case of multiple source domains.”
Learning to select data for transfer learning with Bayesian Optimization (2017, background): “Only recently, many-to-one adaptation (Mansour, 2009; Wu and Huang, 2016) has received some attention, as it replicates the realistic scenario of multiple source domains where performance on the target domain is the foremost objective.”
Multiple Source Adaptation and the Rényi Divergence (2009, methodology): “We showed that solutions based on a simple convex combination of the k source hypotheses h i can perform very poorly and pointed out cases where any such convex com-MANSOUR bination would incur a classiﬁcation error of half, even when each source hypothesis h i makes no error on its domain Q i [12].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “Furthermore, in the case of multi-source domain adaptation [143, 67, 227, 265, 220, 116, 200, 102, 107, 52] different source speciﬁc tasks are jointly exploited in the interest of the target task.”
Scalable Transfer Learning with Expert Models (2020, background): “This can improve both convergence rates (Ben-David et al., 2007; 2010; Blitzer et al., 2008; Du et al., 2017; Kuzborskij & Orabona, 2013; Mansour et al., 2009) and empirical performance (Dai et al.”