Deep Learning of Transferable Representation for Scalable Domain Adaptation
The DOI matches its Crossref record; 49 of the 52 references it cites were found in a registry or an index.
Abstract
Domain adaptation generalizes a learning model across source domain and target domain that are sampled from different distributions. It is widely applied to cross-domain data mining for reusing labeled information and mitigating labeling consumption. Recent studies reveal that deep neural networks can learn abstract feature representation, which can reduce, but not remove, the cross-domain discrepancy. To enhance the invariance of deep representation and make it more transferable across domains, we propose a unified deep adaptation framework for jointly learning transferable representation and classifier to enable scalable domain adaptation, by taking the advantages of both deep learning and optimal two-sample matching. The framework constitutes two inter-dependent paradigms, unsupervised pre-training for effective training of deep models using deep denoising autoencoders, and supervised fine-tuning for effective exploitation of discriminative information using deep neural networks, both learned by embedding the deep representations to reproducing kernel Hilbert spaces (RKHSs) and optimally matching different domain distributions. To enable scalable learning, we develop a linear-time algorithm using unbiased estimate that scales linearly to large samples. Extensive empirical results show that the proposed framework significantly outperforms state of the art methods on diverse adaptation tasks: sentiment polarity prediction, email spam filtering, newsgroup content categorization, and visual object recognition.
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
“Feature-based approaches are widely investigated in transfer learning because of the 2 capability of correcting serious across-domain discrepancy [33], such as TDM scenarios.”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [33]
In the citing paper
“Deep learning-based diagnosis models are beneficial to reducing the cross-domain discrepancy by extracting deep-layer features [33].However, they are unable to adapt serious cross-domain discrepancy in some diagnosis scenarios, such as TDM.”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [33]
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
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
How 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 · cited 5×
“Since SCL, SFA, and CODA are specifically tailored to textual domains, we also investigate two classical transfer learning methods, Transfer Component Analysis ( TCA ) [6] and Geodesic Flow Kernel ( GFK ) [29], which are general methods applicable to various domains.”
BackgroundMethodInfluentialGreedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 2×
“The multi-kernel k (x,x′) = 〈φ (x) , φ (x′)〉 is defined as the convex combination of m characteristic kernels {ku}, K , { k = m∑ u=1 βuku : m∑ u=1 βu = 1, βu > 0,∀u } , (2) where the constraints on coefficients {βu} are imposed to guarantee that the composed multi-kernel k is characteristic.”
BackgroundDomain 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
Learning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505 · cited 2×
“The frequent notations and their descriptions are summarized in Table 1.”
BackgroundMethodSelf-citation(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 3×
“A defense for DAN is that TDN is based on DeCAF features [48], which are also extracted using the deep convolutional neural networks [42].”
MethodInfluential(2012) · MPG.PuRe (Max Planck Society) · doi:10.5555/2188385.2188410 · Cited by 3,603
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 · cited 6×
“…Description Ds,Dt source, target x, x̃ input: original, corrupted d, n #features, #samples z, z̃ activation: original, corrupted c corruption probability W,b deep network parameters λ adaptation penalty fθ, gθ′ encoder, decoder k,β multi-kernel function f supθ supervised classifier: softmax”
BackgroundMethodInfluentialAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 1×
“A multi-kernel learning method is devised for two-sample matching of different domain distributions.”
Method(2011) · Cited by 2,752
Unsupervised Domain Adaptation by Backpropagation
Ganin, Y., & Lempitsky, V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.7495 · Cited by 2,521
Deep domain confusion Maximizing for domain invariance
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014) · arXiv · doi:10.48550/arxiv.1412.3474 · Cited by 2,285
Geodesic flow kernel for unsupervised domain adaptation
Gong, B., Shi, Y., Sha, F., & Grauman, K. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247911 · Cited by 2,093
Transfer Feature Learning with Joint Distribution Adaptation
Long, M., Wang, J., Ding, G., Sun, J., & Yu, P. S. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.274 · Cited by 2,071
Self-citationDomain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach
Glorot, X., Bordes, A., & Bengio, Y. (2011) · HAL · Cited by 2,020
Analysis of Representations for Domain Adaptation
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0022 · Cited by 2,019
(2007) · Cited by 2,018
Correcting Sample Selection Bias by Unlabeled Data
Huang, J., Smola, A. J., Gretton, A., Borgwardt, K. M., & Schölkopf, B. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0080 · Cited by 1,571
(2011) · Cited by 1,192
Exploring Strategies for Training Deep Neural Networks
Larochelle, H., Bengio, Y., Louradour, J., & Lamblin, P. (2009) · doi:10.1145/1577069.1577070 · Cited by 1,095
Optimal kernel choice for large-scale two-sample tests
Gretton, A., Sejdinović, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K., & Sriperumbudur, B. K. (2012) · UCL Discovery (University College London) · Cited by 827
Cross-domain sentiment classification via spectral feature alignment
Pan, S. J., Ni, X., Sun, J.-T., Yang, Q., & Chen, Z. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772767 · Cited by 780
Self-citationDomain Adaptation under Target and Conditional Shift
Zhang, K., Schölkopf, B., Muandet, K., & Wang, Z. (2013) · Max Planck Digital Library · Cited by 760
Adaptation Regularization: A General Framework for Transfer Learning
Long, M., Wang, J., Ding, G., Pan, S. J., & Yu, P. S. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.111 · Cited by 606
Self-citationEquivalence of distance-based and RKHS-based statistics in hypothesis testing
Sejdinovic, D., Sriperumbudur, B., Gretton, A., & Fukumizu, K. (2013) · The Annals of Statistics · doi:10.1214/13-aos1140 · Cited by 582
Domain Transfer Multiple Kernel Learning
Duan, L., Tsang, I. W., & Xu, D. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.114 · Cited by 548
Domain Adaptation: Learning Bounds and Algorithms
Mansour, Y., Mohri, M., & Rostamizadeh, A. (2009) · arXiv · doi:10.48550/arxiv.0902.3430 · Cited by 504 · cited 4×
“F”
BackgroundMethodInfluentialMarginalized Denoising Autoencoders for Domain Adaptation
Chen, M., Xu, Z., Weinberger, K. Q., & Sha, F. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.4683 · Cited by 498
Supervised Representation Learning: Transfer Learning with Deep Autoencoders
Zhuang, F., Cheng, X., Luo, P., Pan, S. J., & He, Q. (2016) · Cited by 431
Co-Training for Domain Adaptation
Chen, M., Weinberger, K. Q., & Blitzer, J. C. (2011) · Cited by 374
Domain Adaptation From Multiple Sources: A Domain-Dependent Regularization Approach
Duan, L., Xu, D., & Tsang, I. W. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2011.2178556 · Cited by 332
Cross-domain collaboration recommendation
Tang, J., Wu, S., Sun, J., & Su, H. (2012) · Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2339530.2339730 · Cited by 292
Self-citationLSDA: Large Scale Detection Through Adaptation
Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., & Saenko, K. (2014) · arXiv · doi:10.48550/arxiv.1407.5035 · Cited by 284 · cited 1×
“The domain adaptation problems involve two types of datasets, one from a source domain and the other from a target domain.”
BackgroundKernel Choice and Classifiability for RKHS Embeddings of Probability Distributions
Fukumizu, K., Gretton, A., Lanckriet, G. R. G., Schölkopf, B., & Sriperumbudur, B. K. (2009) · UCL Discovery (University College London) · Cited by 251
Domain Invariant Transfer Kernel Learning
Long, M., Wang, J., Sun, J., & Yu, P. S. (2015) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2014.2373376 · Cited by 217
Self-citationHybrid Heterogeneous Transfer Learning through Deep Learning
Zhou, J., Pan, S., Tsang, I., & Yan, Y. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8961 · Cited by 197
Shaban, A., & Yousefi, S. (2024) · Springer Optimization and Its Applications · doi:10.1007/978-3-031-53092-0_10 · Cited by 189
Pylearn2: a machine learning research library
Goodfellow, I., Warde-Farley, D., Lamblin, P., Dumoulin, V., Mirza, M., Pascanu, R., Bergstra, J., Bastien, F., & Bengio, Y. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1308.4214 · Cited by 180
Marginalized Denoising Auto-encoders for Nonlinear Representations
Chen, M., Weinberger, K. Q., Sha, F., & Bengio, Y. (2014) · International Conference on Machine Learning · Cited by 154
From bias to opinion: a transfer-learning approach to real-time sentiment analysis
Calais Guerra, P. H., Veloso, A., Meira, W., & Almeida, V. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020438 · Cited by 134
(2013) · Cited by 131
Flexible Transfer Learning under Support and Model Shift
Wang, X., & Schneider, J. (2014) · neural information processing systems · Cited by 96
Covariate Shift in Hilbert Space: A Solution via Sorrogate Kernels
Zhang, K., Zheng, V. W., Wang, Q., Kwok, J. T.-Y., Yang, Q., & Marsic, I. (2013) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 83
B-test: A Non-parametric, Low Variance Kernel Two-sample TestPreprint
Zaremba, W., Gretton, A., & Blaschko, M. B. (2013) · arXiv (Cornell University) · Cited by 79
Kernel Choice and Classifiability for RKHS Embeddings of Probability Distributions
Sriperumbudur, B. K., Fukumizu, K., Gretton, A., Lanckriet, G. R. G., & Schölkopf, B. (2009) · Cited by 35
Research works printed but not linked: 2
- rumelhart, 1986, 1, 318
- ben-david, 0, Analysis of representations for domain adaptation, Proc Adv Neural Inf Process Syst, 137
Cited by
Applications of machine learning to machine fault diagnosis: A review and roadmap
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106587 · Cited by 2,997
Yang, B., Lei, Y., Jia, F., & Xing, S. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.12.051 · Cited by 879
Wasserstein Distance Guided Representation Learning for Domain Adaptation
Shen, J., Qu, Y., Zhang, W., & Yu, Y. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11784 · Cited by 862
Distinguishing between facts and opinions for sentiment analysis: Survey and challenges
Chaturvedi, I., Cambria, E., Welsch, R. E., & Herrera, F. (2018) · Information Fusion · doi:10.1016/j.inffus.2017.12.006 · Cited by 292
Yang, B., Lei, Y., Jia, F., Li, N., & Du, Z. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2953010 · Cited by 282
Metadata
- Authors
- Long, M., Wang, J., Cao, Y., Sun, J., & Yu, P. S.
- Affiliations
- Tsinghua University (CN)
- University of Illinois Chicago (US)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2016-08-01
- Volume
- 28
- Issue
- 8
- Pages
- 2027-2040
- ISSN
- 1041-4347 (ISSN-L)
- OpenAlex
- W2341914330
- Cited by
- 191
- References
- 52
- Citations by year
- 2026: 8 · 2025: 12 · 2024: 14 · 2023: 14 · 2022: 24 · 2021: 32 · 2020: 25 · 2019: 30 · 2018: 16 · 2017: 13 · 2016: 3
- FWCI
- 17.03
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- Funders
- National Natural Science Foundation of China (61325008, 61502265)
- China Postdoctoral Science Foundation (2015T80088)
- National Science and Technology Supporting Program (2015BAH14F02)
- NSF (III-1526499)
- Tsinghua National Laboratory (TNList) Special Fund for Big Data Science and Technology
- 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 › Topic Modeling
- Keywords
- domain adaptation, transferable representations, deep neural network, unsupervised pre-training, deep denoising autoencoder, supervised fine-tuning, scalable learning, linear-time algorithms, polarity classification, email spam detection, visual object recognition
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.