Bayesian Transfer Learning
Not on the map. Why?
Abstract (arXiv)
Transfer learning is a burgeoning concept in statistical machine learning that seeks to improve inference and/or predictive accuracy on a domain of interest by leveraging data from related domains. While the term "transfer learning" has garnered much recent interest, its foundational principles have existed for years under various guises. Prior literature reviews in computer science and electrical engineering have sought to bring these ideas into focus, primarily surveying general methodologies and works from these disciplines. This article highlights Bayesian approaches to transfer learning, which have received relatively limited attention despite their innate compatibility with the notion of drawing upon prior knowledge to guide new learning tasks. Our survey encompasses a wide range of Bayesian transfer learning frameworks applicable to a variety of practical settings. We discuss how these methods address the problem of finding the optimal information to transfer between domains, which is a central question in transfer learning. We illustrate the utility of Bayesian transfer learning methods via a simulation study where we compare performance against frequentist competitors.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 55 of its 116 references that are in the map. First posted on arXiv 20 Dec 2023.
Builds on
55 of 116 references.
References · 55
- 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
- 2018A Survey on Deep Transfer Learningcited by 417
- 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
- 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
- 2018Bayesian Model-Agnostic Meta-Learningcited by 194
- 2018Reinforced Continual Learningcited by 186
- 2020A Survey on Negative Transfercited by 120
- 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
38 more
- 2018An introduction to domain adaptation and transfer learningcited by 112
- 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 100
- 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
- 2021Identifiable Deep Generative Models via Sparse Decodingcited by 54
- 2019The Usual Suspects? Reassessing Blame for VAE Posterior Collapsecited by 52
- 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
- 2022Transfer without Forgettingcited by 44
- 2022Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priorscited by 43
- 2020Transfer Learning in Large-scale Gaussian Graphical Models with False Discovery Rate Controlcited by 38
- 2015A New PAC-Bayesian Perspective on Domain Adaptationcited by 29
- 2020Autoencoding Variational Autoencodercited by 24
- 2020Variational Auto-Regressive Gaussian Processes for Continual Learningcited by 23
- 2019Bayesian Structure Adaptation for Continual Learningcited by 21
- 2021Deep Bayesian Unsupervised Lifelong Learningcited by 21
- 2019Multi-task Learning for Aggregated Data using Gaussian Processescited by 20
- 2021Cooperative learning for multiview analysiscited by 19
- 2022Posterior Collapse of a Linear Latent Variable Modelcited by 18
- 2018Optimal Bayesian Transfer Learningcited by 17
- 2017PAC-Bayes and Domain Adaptationcited by 16
- 2022PAC-Bayesian Domain Adaptation Bounds for Multiclass Learnerscited by 13
- 2020Escaping the curse of dimensionality in Bayesian model based clusteringcited by 12
- 2019Multi-resolution Multi-task Gaussian Processescited by 11
- 2018Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count datacited by 10
- 2021GAN Cocktail: mixing GANs without dataset accesscited by 8
- 2014Bayesian Inference and Testing of Group Differences in Brain Networkscited by 6
- 2019Bayesian Factor Analysis for Inference on Interactionscited by 5
- 2016Large Covariance Estimation for Compositional Data via Composition-Adjusted Thresholdingcited by 4
- 2016Embracing the Blessing of Dimensionality in Factor Modelscited by 4
- 2018Bayesian Constraint Relaxationcited by 4
- 2023Inferring Covariance Structure from Multiple Data Sources via Subspace Factor Analysiscited by 4
- 2016Functional Autoregression for Sparsely Sampled Datacited by 3
- 2016Bayesian inference for multiple Gaussian graphical models with application to metabolic association networkscited by 3
- 2021A Proximal Distance Algorithm for Likelihood-Based Sparse Covariance Estimationcited by 3
- 2023Identifiable and interpretable nonparametric factor analysiscited by 3
- 2021Bayesian Transfer Learning: An Overview of Probabilistic Graphical Models for Transfer Learningcited by 2
- 2021Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsycited by 2
- 2021Bayesian Nested Latent Class Models for Cause-of-Death Assignment using Verbal Autopsies Across Multiple Domainscited by 2
- 2023Graphical Dirichlet Process for Clustering Non-Exchangeable Grouped Datacited by 2
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.