The DOI matches its Crossref record; 89 of the 90 references it cites were found in a registry or an index.
A Survey on Transfer Learning
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 3,844
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
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 · cited 1×
“Although Ben-David et al. [61] showed experimentally that SCL can reduce the difference between domains; how to select the pivot features is difficult and domain dependent.”
Background(2007) · Cited by 2,018
Boosting for transfer learning
Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273521 · Cited by 1,724 · cited 9×
“Dai et al. [6] proposed a boosting algorithm, TrAdaBoost, which is an extension of the AdaBoost algorithm, to address the inductive transfer learning problems.”
BackgroundMethodInfluentialSelf-citationImproving predictive inference under covariate shift by weighting the log-likelihood function
Shimodaira, H. (2000) · Journal of Statistical Planning and Inference · doi:10.1016/s0378-3758(00)00115-4 · Cited by 1,678
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 · cited 3×
“It can be proved that i ¼ P ðx S i Þ P ðx T i Þ [32] .”
BackgroundMethodDataset Shift in Machine Learning
(2008) · doi:10.7551/mitpress/9780262170055.001.0001 · Cited by 1,553 · cited 2×
“The first context can be referred to as instance-based transfer learning (or instance transfer) approach [6], [28], [29], [30], [31], [24], [32], [33], [34], [35], which assumes that certain parts of the data in the source domain can be reused for learning in the target domain by reweighting.”
BackgroundDomain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543
Self-taught learning: transfer learning from unlabeled data
Raina, R., Battle, A., Lee, H., Packer, B., & Ng, A. Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273592 · Cited by 1,510 · cited 4×
“Raina et al. [74] and Dai et al. [36], [28] proposed to use transfer learning techniques to learn text data across domains, respectively.”
BackgroundMethodResultInfluentialRegularized multi--task learning
Evgeniou, T., & Pontil, M. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014067 · Cited by 1,433 · cited 2×
“Evgeniou and Pontil [48] borrowed the idea of HB to SVMs for multitask learning.”
BackgroundFrustratingly Easy Domain Adaptation
Daumé, H. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0907.1815 · Cited by 1,383
Argyriou, A., Evgeniou, T., & Pontil, M. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0010 · Cited by 1,333
Caruana, R. (1998) · Cited by 1,110
10 CHALLENGING PROBLEMS IN DATA MINING RESEARCH
YANG, Q., & WU, X. (2006) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622006002258 · Cited by 930 · 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-citationMulti-task Gaussian Process Prediction
Bonilla, E. V., Chai, K. M. A., & Williams, C. K. I. (2007) · Cited by 923
Domain Adaptation for Statistical Classifiers
Daume III, H., & Marcu, D. (2006) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1872 · Cited by 816 · cited 1×
“The latter case of thetransductive transfer learning setting is related to domain adaptation for knowledge transfer in text classification [23] and sample selection bias [24] or co-variate shift [25], whose assumptions are”
BackgroundLearning and evaluating classifiers under sample selection bias
Zadrozny, B. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015425 · Cited by 800
Instance Weighting for Domain Adaptation in NLP
Jiang, J., & Zhai, C. (2007) · Cited by 765
Direct importance estimation with model selection and its application to covariate shift adaptation
Sugiyama, M., Nakajima, S., Kashima, H., von Bünau, P., & Kawanabe, M. (2009) · Cited by 679
Transfer learning via dimensionality reduction
Pan, S. J., Kwok, J. T.-Y., & Yang, Q. (2008) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 653
Self-citationFrustratingly Easy Domain Adaptation
Daum, H. (2007) · Cited by 601
To transfer or not to transfer
Rosenstein, M. T. (2005) · neural information processing systems · Cited by 430
Exploiting Task Relatedness for Multiple Task Learning
Ben-David, S., & Schuller, R. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-45167-9_41 · Cited by 425 · cited 1×
“Some works have been exploited to analyze relatedness among tasks and task clustering techniques, such as [71], [72], which may help provide guidance on how to avoid negative transfer automatically.”
BackgroundLearning Bounds for Domain Adaptation
Blitzer, J. C., Crammer, K., Kulesza, A., Pereira, F. M. B., & Wortman, J. R. (2007) · Cited by 393
Discriminative learning for differing training and test distributions
Bickel, S., Brückner, M., & Scheffer, T. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273507 · Cited by 387 · cited 2×
“Bickel et al. [33] combined the two steps in a unified framework by deriving a kernel-logistic regression classifier.”
BackgroundCan movies and books collaborate?: cross-domain collaborative filtering for sparsity reduction
Li, B., Yang, Q., & Xue, X. (2009) · Cited by 361
Self-citationTransfer learning for collaborative filtering via a rating-matrix generative model
Li, B., Yang, Q., & Xue, X. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553454 · Cited by 340
Self-citationLearning to learn with the informative vector machine
Lawrence, N. D., & Platt, J. C. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015382 · Cited by 338 · cited 2×
“approach [45], [46], [47], [48], [49], which assumes that the”
BackgroundMethodCo-clustering based classification for out-of-domain documents
Dai, W., Xue, G.-R., Yang, Q., & Yu, Y. (2007) · Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1281192.1281218 · Cited by 331
Self-citationKnowledge transfer via multiple model local structure mapping
Gao, J., Fan, W., Jiang, J., & Han, J. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401928 · Cited by 330 · cited 5×
“Gao et al. [49] proposed a locally weighted ensemble learning framework to combine multiple models for transfer learning, where the weights are dynamically assigned according to a model's predictive power on each test example in the target domain.”
BackgroundMethodInfluentialTransferring naive bayes classifiers for text classification
Dai, W., Xue, G.-R., Yang, Q., & Yu, Y. H. (2007) · Cited by 325
Self-citationMapping and revising Markov logic networks for transfer learning
Mihalkova, L. S., Huynh, T. N., & Mooney, R. J. (2007) · Cited by 309
Improving SVM accuracy by training on auxiliary data sources
Wu, P., & Dietterich, T. G. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015436 · Cited by 301 · cited 2×
“Wu and Dietterich [53] integrated the source domain (auxiliary) data an Support Vector Machine (SVM) framework for improving the classification performance.”
BackgroundConstructing informative priors using transfer learning
Raina, R., Ng, A. Y., & Koller, D. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143934 · Cited by 299 · cited 3×
“Raina et al. [74] and Dai et al. [36], [28] proposed to use transfer learning techniques to learn text data across domains, respectively.”
BackgroundManifold alignment using Procrustes analysis
Wang, C., & Mahadevan, S. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390297 · Cited by 258 · cited 2×
“In [44], Wang and Mahadevan proposed a Procrustes analysis-based approach to manifold alignment without correspondences, which can be used to transfer the knowledge across domains via the aligned manifolds.”
BackgroundMethodTask Clustering and Gating for Bayesian Multitask Learning
Bakker, B., & Heskes, T. (2003) · Radboud Repository (Radboud University) · Cited by 231
Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390182 · Cited by 223 · cited 5×
“STC tries to learn a common feature space across domains, which helps in clustering in the target domain.”
BackgroundMethodInfluentialSelf-citationA high-performance semi-supervised learning method for text chunking
Ando, R. K., & Zhang, T. (2005) · Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05 · doi:10.3115/1219840.1219841 · Cited by 223 · cited 2×
“A second case can be referred to as feature-representation-transfer approach [22], [36], [37], [38], [39], [8], [40], [41], [42], [43], [44].”
BackgroundDeep transfer via second-order Markov logic
Davis, J., & Domingos, P. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553402 · Cited by 222 · cited 2×
“Davis and Domingos [52] proposed an approach to transferring relational knowledge based on a form of second-order Markov logic.”
BackgroundText classification without negative examples revisit
Fung, G. P. C., Yu, J. X., Lu, H., & Yu, P. S. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.16 · Cited by 221
Multi-task feature and kernel selection for SVMs
Jebara, T. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015426 · Cited by 218 · cited 2×
“A second case can be referred to as feature-representation-transfer approach [22], [36], [37], [38], [39], [8], [40], [41], [42], [43], [44].”
BackgroundMethodA Spectral Regularization Framework for Multi-Task Structure Learning
Argyriou, A. A., Pontil, M., Ying, Y., & Micchelli, C. A. (2007) · Cited by 215
Cross-domain transfer for reinforcement learning
Taylor, M. E., & Stone, P. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273607 · Cited by 204 · cited 1×
“There has been a large amount of work on transfer learning for reinforcement learning in the machine learning literature (e.g., [9], [10]).”
BackgroundLogistic regression with an auxiliary data source
Liao, X., Xue, Y., & Carin, L. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102415 · Cited by 203 · cited 3×
“The first context can be referred to as instance-based transfer learning (or instance transfer) approach [6], [28], [29], [30], [31], [24], [32], [33], [34], [35], which assumes that certain parts of the data in the source domain can be reused for learning in the target domain by reweighting.”
BackgroundA Comparative Study of Methods for Transductive Transfer Learning
Arnold, A. O., Nallapati, R., & Cohen, W. W. (2007) · doi:10.1109/icdmw.2007.2 · Cited by 200
A Comparative Study of Methods for Transductive Transfer Learning
Arnold, A., Nallapati, R., & Cohen, W. W. (2007) · Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007) · doi:10.1109/icdmw.2007.109 · Cited by 198 · cited 3×
“Arnold et al. [58] proposed to use transductive transfer learning methods to solve name-entity recognition problems.”
BackgroundMethodInfluentialTopic-bridged PLSA for cross-domain text classification
Xue, G.-R., Dai, W., Yang, Q., & Yu, Y. (2008) · Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1390334.1390441 · Cited by 193
Self-citationAdaptive Temporal Radio Maps for Indoor Location Estimation
Yin, J., Yang, Q., & Ni, L. (2005) · Third IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2005.7 · Cited by 185
Self-citationLearning Gaussian Process Kernels via Hierarchical Bayes
Schwaighofer, A., Tresp, V., & Yu, K. (2004) · Cited by 172
Learning a meta-level prior for feature relevance from multiple related tasks
Lee, S.-I., Chatalbashev, V., Vickrey, D., & Koller, D. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273558 · Cited by 161
Classifier Ensembles with a Random Linear Oracle
Kuncheva, L. I., & Rodriguez, J. J. (2007) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.1016 · Cited by 160
Actively Transfer Domain Knowledge
Shi, X., Fan, W., & Ren, J. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87481-2_23 · Cited by 134 · cited 3×
“In [6], [84], [49], the authors used the 20 Newsgroups data 12 as one of the evaluation data sets.”
MethodBayesian multiple instance learning: automatic feature selection and inductive transfer
Raykar, V. C., Krishnapuram, B., Bi, J., Dündar, M., & Rao, R. B. (2008) · International Conference on Machine Learning · doi:10.1145/1390156.1390258 · Cited by 134 · cited 1×
“In [81], Raykar et al. proposed a novel Bayesian multipleinstance learning algorithm, which can automatically identify the relevant feature subset and use inductive transfer for learning multiple, but conceptually related, classifiers, for computer aided design (CAD).”
BackgroundSpectral domain-transfer learning
Xiao, L., Dai, W., Xue, G.-R., Yang, Q., & Yu, Y. H. (2008) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1401890.1401951 · Cited by 132 · cited 1×
“In [64], Ling et al. proposed a spectral classification framework for cross-domain transfer learning problem, where the objective function is introduced to seek consistency between the in-domain supervision and the out-of-domain intrinsic structure.”
BackgroundSelf-citationTransferred Dimensionality Reduction
Wang, Z., Song, Y., & Zhang, C. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87481-2_36 · Cited by 122 · cited 4×
“TDA first applies clustering methods to generate pseudoclass labels for the target unlabeled data.”
BackgroundMethodInfluentialCan chinese web pages be classified with english data source?
Xiao, L., Xue, G.-R., Dai, W., Jiang, Y., Yang, Q., & Yu, Y. H. (2008) · International World Wide Web Conference (WWW) · doi:10.1145/1367497.1367628 · Cited by 122
Self-citationAdaptive localization in a dynamic WiFi environment through multi-view learning
Pan, S. J., Kwok, J. T.-Y., Yang, Q., & Pan, J. J. (2007) · Cited by 121
Self-citationA Lazy Approach to Associative Classification
Baralis, E., Chiusano, S., & Garza, P. (2008) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.190677 · Cited by 111
A New Text Categorization Technique Using Distributional Clustering and Learning Logic
Al-Mubaid, H., & Umair, S. A. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.135 · Cited by 107 · cited 1×
“example is Web-document classification [3], [4], [5], where”
BackgroundTransferring multi-device localization models using latent multi-task learning
Zheng, V. W., Pan, S. J., Yang, Q., & Pan, J. J. (2008) · Cited by 107
Self-citationEstimating Location Using Wi-Fi
Yang, Q., Pan, S. J., & Zheng, V. W. (2008) · IEEE Intelligent Systems · doi:10.1109/mis.2008.4 · Cited by 101 · cited 1×
“A second data set was made available through the ICDM-2007 Contest, in which a task was to estimate a WiFi client's indoor locations using the WiFi signal data obtained over different periods of time [83].”
MethodSelf-citationTransfer Learning by Mapping with Minimal Target Data
Mihalkova, L. S., & Mooney, R. J. (2008) · Cited by 99
Efficient classification across multiple database relations: a CrossMine approach
Yin, X., Han, J., Yang, J., & Yu, P. S. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.94 · Cited by 94
Transferring localization models over time
Zheng, V. W., Xiang, E. W., Yang, Q., & Shen, D. (2008) · Cited by 91
Self-citationTransfer learning for WiFi-based indoor localization
Pan, S. J., Zheng, V. W., Yang, Q., & Hu, D. H. (2008) · National Conference on Artificial Intelligence · Cited by 89
Self-citationTransfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling
Ramon, J., Driessens, K., & Croonenborghs, T. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74958-5_70 · Cited by 87 · cited 1×
“There has been a large amount of work on transfer learning for reinforcement learning in the machine learning literature (e.g., [9], [10]).”
BackgroundTransfer Learning using Kolmogorov Complexity: Basic Theory and Empirical Evaluations
Mahmud, M., & Ray, S. R. (2007) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 87
Transferring localization models across space
Pan, S. J., Shen, D., Yang, Q., & Kwok, J. T.-Y. (2008) · Cited by 86
Self-citationAn Algorithm for Transfer Learning in a Heterogeneous Environment
Argyriou, A., Maurer, A., & Pontil, M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87479-9_23 · Cited by 75 · cited 3×
“In a follow-up work, Argyriou et al. [41] proposed a spectral regularization framework on matrices for multitask structure learning.”
BackgroundGraph-Based Domain Mapping for Transfer Learning in General Games
Kuhlmann, G., & Stone, P. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74958-5_20 · Cited by 73 · cited 1×
“For example, Kuhlmann and Stone [85] proposed a graph-based method for identifying previously encountered games, and applied this technique to automate domain mapping for value function transfer and speed up reinforcement learning on variants of previously played games.”
MethodModeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer
Eaton, E., Desjardins, M. E., & Lane, T. D. R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87479-9_39 · Cited by 72 · cited 1×
“Recently, Eaton et al. [69] proposed a novel graph-based method for knowledge transfer, where the relationships between source tasks are modeled by embedding the set of learned source models in a graph using transferability as the metric.”
MethodTest-cost sensitive classification on data with missing values
Yang, Q., Ling, C. X., Chai, X., & Pan, R. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.84 · Cited by 66
Self-citationCombining Subclassifiers in Text Categorization: A DST-Based Solution and a Case Study
Sarinnapakorn, K., & Kubát, M. (2007) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.190663 · Cited by 64 · cited 1×
“One example is Web-document classification [3], [4], [5], where our goal is to classify a given Web document into several predefined categories.”
BackgroundAn Improved Categorization of Classifier’s Sensitivity on Sample Selection Bias
Fan, W., Davidson, I. A. K., Zadrozny, B., & Yu, P. S. (2006) · Proceedings · doi:10.1109/icdm.2005.24 · Cited by 63
Bridged Refinement for Transfer Learning
Xing, D., Dai, W., Xue, G.-R., & Yu, Y. H. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74976-9_31 · Cited by 58 · cited 1×
“In [63], Xing et al. proposed a novel algorithm known as bridged refinement to correct the labels predicted by a shiftunaware classifier toward a target distribution and take the mixture distribution of the training and test data as a bridge to better transfer from the training data to the test…”
BackgroundXingquan Zhu, A., & Wu, X. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.155 · Cited by 51
Kernel-Based Inductive Transfer
Rückert, U., & Krämer, S. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87481-2_15 · Cited by 44 · cited 1×
“[54] designed a kernel-based approach to inductive transfer, which aims at finding a suitable kernel for the target data.”
BackgroundTheory Refinement of Bayesian Networks with Hidden Variables
Ramachandran, S., & Mooney, R. J. (1998) · Cited by 26
Transferring Knowledge from Another Domain for Learning Action Models
Zhuo, H. H., Yang, Q., Hu, D. H., & Li, L. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89197-0_115 · Cited by 19 · cited 1×
“Zhuo et al. [80] studied how to transfer domain knowledge to learn relational action models across domains in automated planning.”
BackgroundSelf-citationLearning by Translating. A Course in Translation: English to Italian & Italian to English
Fabio, E. G. D., Laviosa, S., & Cleverton, V. (2004) · Italica · doi:10.2307/27668955 · Cited by 2
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.