Domain adaptation under structural causal models
Y Chen, P Bühlmann - Journal of Machine Learning Research, 2021 - jmlr.org
Domain adaptation (DA) arises as an important problem in statistical machine learning when
the source data used to train a model is different from the target data used to test the model …
the source data used to train a model is different from the target data used to test the model …
Partial identifiability for domain adaptation
Unsupervised domain adaptation is critical to many real-world applications where label
information is unavailable in the target domain. In general, without further assumptions, the …
information is unavailable in the target domain. In general, without further assumptions, the …
Partial disentanglement for domain adaptation
Unsupervised domain adaptation is critical to many real-world applications where label
information is unavailable in the target domain. In general, without further assumptions, the …
information is unavailable in the target domain. In general, without further assumptions, the …
Combating negative transfer from predictive distribution differences
Domain adaptation (DA), which leverages labeled data from related source domains, comes
in handy when the label information of the target domain is scarce or unavailable. However …
in handy when the label information of the target domain is scarce or unavailable. However …
Learning causal representations for robust domain adaptation
In this study, we investigate a challenging problem, namely, robust domain adaptation,
where data from only a single well-labeled source domain are available in the training …
where data from only a single well-labeled source domain are available in the training …
Domain adaptation with conditional transferable components
Abstract Domain adaptation arises in supervised learning when the training (source domain)
and test (target domain) data have different distributions. Let X and Y denote the features …
and test (target domain) data have different distributions. Let X and Y denote the features …
Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a
labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA …
labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA …
Data-driven approach to multiple-source domain adaptation
P Stojanov, M Gong, J Carbonell… - The 22nd International …, 2019 - proceedings.mlr.press
A key problem in domain adaptation is determining what to transfer across different
domains. We propose a data-driven method to represent these changes across multiple …
domains. We propose a data-driven method to represent these changes across multiple …
Exploiting the intrinsic neighborhood structure for source-free domain adaptation
S Yang, J Van de Weijer… - Advances in neural …, 2021 - proceedings.neurips.cc
Abstract Domain adaptation (DA) aims to alleviate the domain shift between source domain
and target domain. Most DA methods require access to the source data, but often that is not …
and target domain. Most DA methods require access to the source data, but often that is not …
Domain adaptation with invariant representation learning: What transformations to learn?
Unsupervised domain adaptation, as a prevalent transfer learning setting, spans many real-
world applications. With the increasing representational power and applicability of neural …
world applications. With the increasing representational power and applicability of neural …