A Survey on Transfer Learning
The DOI matches its Crossref record; 89 of the 90 references it cites were found in a registry or an index.
Abstract
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.
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
“These are perturbed versions of test inputs which seem almost indistinguishable from the original test input to a human, but fool the trained model [70, 441].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [70]
In the citing paper
“The rationale is to make the data distributions from different subjects more similar, and hence a classifier trained on the auxiliary data would have a better chance to perform well on the new subject.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [23]
In the citing paper
“Fortunately, transfer learning is concerned to overcome such weaknesses by applying the knowledge learned from one or multiple tasks to other related but novel ones [27].”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [27]
In the citing paper
“Transfer learning is able to get the above purpose, in which the knowledge from one or more diagnosis tasks can be reused to other related but different ones [27].”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [27]
In the citing paper
“TL has many advantages in the development of ML algorithms, such as shorter training times and the enhanced robustness of using models that have already passed initial tests.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [127]
14 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 1×
“Among these, a closely related learning technique to transfer learning is the multitask learning framework [21], which tries to learn multiple tasks simultaneously even when they are different.”
BackgroundTop 10 algorithms in data mining
Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G. J., Ng, A., Liu, B., Yu, P. S., et al. (2008) · Knowledge and Information Systems · doi:10.1007/s10115-007-0114-2 · Cited by 5,667 · cited 1×
“ATA mining and machine learning technologies have already achieved significant success in many knowledge engineering areas including classification, regression, and clustering (e.g., [1], [2]).”
BackgroundSelf-citationCombining labeled and unlabeled data with co-training
Blum, A., & Mitchell, T. (1998) · Proceedings of the eleventh annual conference on Computational learning theory · doi:10.1145/279943.279962 · Cited by 5,495
Domain Adaptation via Transfer Component Analysis
Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2091281 · Cited by 4,753 · cited 2×
“Finally, on the WiFi localization data set, we show the comparison results reported in [67], where the baseline is a regularized least square regression model (RLSR), which is a standard regression model, and KPCA, which represents to apply RLSR on the new representations of the data learned by…”
MethodSelf-citationSemi-Supervised Learning Literature Survey
Zhu, X. (2005) · Minds at UW (University of Wisconsin) · Cited by 4,505
Text classification from labeled and unlabeled documents using EM
Nigam, K., Mccallum, A. K., Thrun, S., & Mitchell, T. (2000) · Machine Learning · doi:10.1023/a:1007692713085 · Cited by 2,736
Transductive Inference for Text Classification using Support Vector Machines
Joachims, T. (1999) · Cited by 2,723
Richardson, M., & Domingos, P. (2006) · Machine Learning · doi:10.1007/s10994-006-5833-1 · Cited by 2,676 · cited 1×
“MLNs [56] is a powerful formalism, which combines the compact expressiveness of first-order logic with flexibility of probability, for statistical relational learning.”
BackgroundEfficient sparse coding algorithms
Lee, H., Battle, A., Raina, R., & Ng, A. Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0105 · Cited by 2,394
Research works printed but not linked: 3
- 1998, Learning to Learn
- 10.5555/2981562.2981582 · doi:10.5555/2981562.2981582
- Joachims, Transductive Inference for Text Classification Using Support Vector Machines, 200
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
“, 2012) specialised on Transfer Learningfrom one dataset to another (e.g., Caruana, 1997; Schmidhuber, 2004; Pan and Yang, 2010).”
BackgroundDermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
“Federated transfer learning [419] is another concept that considers challenging scenarios in which data parties share only a partial overlap in the user space or the feature space, and leverage existing transfer learning techniques [314] to build models collaboratively.”
BackgroundSelf-citation
Metadata
- Authors
- Pan, S. J., & Yang, Q.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2010-10
- Volume
- 22
- Issue
- 10
- Pages
- 1345-1359
- ISSN
- 1041-4347 (ISSN-L)
- OpenAlex
- W2165698076
- Semantic Scholar
- a25fbcbbae1e8f79c4360d26aa11a3abf1a11972
- Cited by
- 23,387
- References
- 90
- Citations by year
- 2026: 1673 · 2025: 2106 · 2024: 2284 · 2023: 2499 · 2022: 2654 · 2021: 3152 · 2020: 2705 · 2019: 2137 · 2018: 1346 · 2017: 776 · 2016: 516 · 2015: 429 · 2014: 369 · 2013: 293 · 2012: 211
- FWCI
- 160.24
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- Defense Advanced Research Projects Agency
- 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 › Reinforcement Learning in Robotics
- Keywords
- transfer learning, domain adaptation, multi-task learning, sample selection bias, covariate shift, knowledge transfer, classification, regression analysis, clustering, distribution shift
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
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.