A theoretical framework for deep transfer learning
The DOI matches its Crossref record; 49 of the 52 references it cites were found in a registry or an index.
Abstract
We generalize the notion of PAC learning to include transfer learning. In our framework, the linkage between the source and the target tasks is a result of having the sample distribution of all classes drawn from the same distribution of distributions, and by restricting all source and a target concepts to belong to the same hypothesis subclass. We have two models: an adversary model and a randomized model. In the adversary model, we show that for binary classification, conventional PAC-learning is equivalent to the new notion of PAC-transfer and to transfer generalization of the VC-dimension. For regression, we show that PAC-transferability may exist even in the absence of PAC-learning. In both adversary and randomized models, we provide PAC-Bayesian and VC-style generalization bounds to transfer learning. In the randomized model, we provide bounds specifically derived for Deep Learning. A wide discussion on the tradeoffs between the different involved parameters in the bounds is provided. We demonstrate both cases in which transfer does not reduce the sample size (‘trivial transfer’) and cases in which the sample size is reduced (‘non-trivial transfer’).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“With TL the required sample size can be significantly reduced [104].”
From Multimodal deep learning for biomedical data fusion: a review (2022) · cites this paper as [104]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 2×
“This can be seen in the bottleneck effect demonstrated in Taigman et al. (2015), where creating a lower-dim representation improves transfer performance.”
BackgroundMethodSelf-citationHow transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
A theory of learning from different domains
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010) · Machine Learning · doi:10.1007/s10994-009-5152-4 · Cited by 3,515
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279
Research works printed but not linked: 2
- Donahue J. , Jia Y. , Vinyals O. , Hoffman J. , Zhang N. , Tzeng E. & Darrell T. (2013) Decaf: a deep convolutional activation feature for generic visual recognition. CoRR, abs/1310.1531. · arXiv
- Sukhbaatar S. & Fergus R. (2014) Learning from noisy labels with deep neural networks. CoRR, abs/1406.2080. · arXiv
Cited by
Low-Shot Visual Recognition by Shrinking and Hallucinating Features
Hariharan, B., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.328 · Cited by 792
“[16] provide some theoretical justification for this finding.”
BackgroundMultimodal deep learning for biomedical data fusion: a review
Stahlschmidt, S. R., Ulfenborg, B., & Synnergren, J. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab569 · Cited by 766
“With TL the required sample size can be significantly reduced [104].”
BackgroundTransfusion: Understanding Transfer Learning for Medical Imaging
Raghu, M., Zhang, C., Kleinberg, J. M., & Bengio, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07208 · Cited by 613
Meta-Learning without MemorizationPreprint
Yin, M., Tucker, G., Zhou, M., Levine, S., & Finn, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.03820 · Cited by 156
“More recent research shows that, with tightened generalization bounds as the training objective, the algorithms can reduce the test error for mutually-exclusive tasks (Galanti et al., 2016; Amit & Meir, 2018).”
BackgroundFew-Shot Learning via Learning the Representation, ProvablyPreprint
Du, S. S., Hu, W. P., Kakade, S. M., Lee, J. D., & Lei, Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09434 · Cited by 236
“Lastly, we remark that there are analyses for other representation learning schemes (Arora et al., 2019, McNamara and Balcan, 2017, Galanti et al., 2016, Alquier et al., 2016, Denevi et al., 2018).”
Background
Metadata
- Authors
- Galanti, T., Wolf, L., & Hazan, T.
- Affiliations
- Tel Aviv University (IL)
- Technion – Israel Institute of Technology (IL)
- Corresponding author
- Wolf, Lior
- Venue
- Information and Inference
- Publisher
- Oxford University Press (OUP)
- Published
- 2016-04-28
- Volume
- 5
- Issue
- 2
- Pages
- 159-209
- ISSN
- 2049-8764 (ISSN-L)
- 2049-8772
- OpenAlex
- W2342750929
- Cited by
- 29
- References
- 52
- Citations by year
- 2025: 1 · 2024: 1 · 2023: 2 · 2022: 1 · 2021: 6 · 2020: 4 · 2019: 7 · 2018: 3 · 2017: 4
- FWCI
- 3.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Information and Inference A Journal of the IMA (publishedVersion)
- HighWire Press Open Archive (submittedVersion)
- Funders
- German-Israeli Foundation for Scientific Research and Development
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- transfer learning, PAC learning, VC dimension, PAC-Bayesian bounds, generalization bounds, deep learning, binary classification, regression analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A theoretical framework for deep transfer learning. https://app.cochat.ai/papers/10.1093/imaiai/iaw008
- The paper
- Galanti, T., Wolf, L., & Hazan, T. (2016). A theoretical framework for deep transfer learning. Information and Inference. https://doi.org/10.1093/imaiai/iaw008
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.