A survey on deep transfer learning and beyond
Deep transfer learning (DTL), which incorporates new ideas from deep neural networks into
transfer learning (TL), has achieved excellent success in computer vision, text classification …
transfer learning (TL), has achieved excellent success in computer vision, text classification …
A closer look at smoothness in domain adversarial training
Abstract Domain adversarial training has been ubiquitous for achieving invariant
representations and is used widely for various domain adaptation tasks. In recent times …
representations and is used widely for various domain adaptation tasks. In recent times …
Free lunch for domain adversarial training: Environment label smoothing
A fundamental challenge for machine learning models is how to generalize learned models
for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features …
for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features …
Non-iid transfer learning on graphs
Transfer learning refers to the transfer of knowledge or information from a relevant source
domain to a target domain. However, most existing transfer learning theories and algorithms …
domain to a target domain. However, most existing transfer learning theories and algorithms …
Optimizing data collection for machine learning
Modern deep learning systems require huge data sets to achieve impressive performance,
but there is little guidance on how much or what kind of data to collect. Over-collecting data …
but there is little guidance on how much or what kind of data to collect. Over-collecting data …
Discriminability and transferability estimation: a bayesian source importance estimation approach for multi-source-free domain adaptation
Source free domain adaptation (SFDA) transfers a single-source model to the unlabeled
target domain without accessing the source data. With the intelligence development of …
target domain without accessing the source data. With the intelligence development of …
Low budget active learning via wasserstein distance: An integer programming approach
Active learning is the process of training a model with limited labeled data by selecting a
core subset of an unlabeled data pool to label. The large scale of data sets used in deep …
core subset of an unlabeled data pool to label. The large scale of data sets used in deep …
Riemannian representation learning for multi-source domain adaptation
Abstract Multi-Source Domain Adaptation (MSDA) aims at training a classification model that
achieves small target error, by leveraging labeled data from multiple source domains and …
achieves small target error, by leveraging labeled data from multiple source domains and …
Distribution-informed neural networks for domain adaptation regression
In this paper, we study the problem of domain adaptation regression, which learns a
regressor for a target domain by leveraging the knowledge from a relevant source domain …
regressor for a target domain by leveraging the knowledge from a relevant source domain …
Kl guided domain adaptation
Domain adaptation is an important problem and often needed for real-world applications. In
this problem, instead of iid training and testing datapoints, we assume that the source …
this problem, instead of iid training and testing datapoints, we assume that the source …