Skip to main content
SpringerLink
Log in

Transfer Learning Techniques

  • Chapter
  • First Online:
Big Data Technologies and Applications

Abstract

Machine learning and data mining techniques have been used in numerous real-world applications. An assumption of traditional machine learning methodologies is the training data and testing data are taken from the same domain, such that the input feature space and data distribution characteristics are the same. However, in some real-world machine learning scenarios, this assumption does not hold. There are cases where training data is expensive or difficult to collect. Therefore, there is a need to create high-performance learners trained with more easily obtained data from different domains. This methodology is referred to as transfer learning. This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied to transfer learning. Lastly, there is information listed on software downloads for various transfer learning solutions and a discussion of possible future research work. The transfer learning solutions surveyed are independent of data size and can be applied to big data environments.

This chapter has been adopted from the Journal of Big Data, Borko Furht and Taghi Khoshgoftar, Editors-in-Chief. Springer, June 2016.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Witten IH, Frank E. Data mining, practical machine learning tools and techniques. 3rd ed. San Francisco, CA: Morgan Kaufmann Publishers; 2011.

    MATH  Google Scholar 

  2. Shimodaira H. Improving predictive inference under covariate shift by weighting the log-likelihood function. J Stat Plan Inference. 2000;90(2):227–44.

    Article  MathSciNet  MATH  Google Scholar 

  3. Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345–59.

    Article  Google Scholar 

  4. Wang C, Mahadevan S. Heterogeneous domain adaptation using manifold alignment. In: Proceedings of the twenty-second international joint conference on artificial intelligence, vol. 2; 2011. p. 1541–6.

    Google Scholar 

  5. Duan L, Xu D, Tsang IW. Learning with augmented features for heterogeneous domain adaptation. IEEE Trans Pattern Anal Mach Intell. 2012;36(6):1134–48.

    Google Scholar 

  6. Kulis B, Saenko K, Darrell T. What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: IEEE 2011 conference on computer vision and pattern recognition; 2011. p. 1785–92.

    Google Scholar 

  7. Zhu Y, Chen Y, Lu Z, Pan S, Xue G, Yu Y, Yang Q. Heterogeneous transfer learning for image classification. Proc Nat Conf Artif Intell. 2011;2:1304–9.

    Google Scholar 

  8. Harel M, Mannor S. Learning from multiple outlooks. In: Proceedings of the 28th international conference on machine learning; 2011. p. 401–408.

    Google Scholar 

  9. Nam J, Kim S. Heterogeneous defect prediction. In: Proceedings of the 2015 10th joint meeting on foundations of software engineering; 2015. p. 508–19.

    Google Scholar 

  10. Zhou JT, Tsang IW, Pan SJ Tan M. Heterogeneous domain adaptation for multiple classes. In: International conference on artificial intelligence and statistics; 2014. p. 1095–103.

    Google Scholar 

  11. Prettenhofer P, Stein B. Cross-language text classification using structural correspondence learning. In: Proceedings of the 48th annual meeting of the association for computational linguistics; 2010. p. 1118–27.

    Google Scholar 

  12. Zhou JT, Pan S, Tsang IW, Yan Y. Hybrid heterogeneous transfer learning through deep learning. Proc Nat Conf Artif Intell. 2014;3:2213–20.

    Google Scholar 

  13. Taylor ME, Stone P. Transfer learning for reinforcement learning domains: a survey. JMLR. 2009;10:1633–85.

    MathSciNet  MATH  Google Scholar 

  14. Daumé H III. Frustratingly easy domain adaptation. In: Proceedings of 2007 ACL; 2007. p. 256–63.

    Google Scholar 

  15. Chattopadhyay R, Ye J, Panchanathan S, Fan W, Davidson I. Multi-source domain adaptation and its application to early detection of fatigue. ACM Trans Knowl Discov Data. 2011;6(4):18.

    Google Scholar 

  16. Gong B, Shi Y, Sha F, Grauman K. Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings of the 2012 IEEE conference on computer vision and pattern recognition; 2012. p. 2066–73.

    Google Scholar 

  17. Blitzer J, McDonald R, Pereira F. Domain adaptation with structural correspondence learning. In: Proceedings of the 2006 conference on empirical methods in natural language processing; 2006. p. 120–28.

    Google Scholar 

  18. Cook DJ, Feuz KD, Krishnan NC. Transfer learning for activity recognition: a survey. Knowl Inf Syst. 2012;36(3):537–56.

    Article  Google Scholar 

  19. Feuz KD, Cook DJ. Transfer learning across feature-rich heterogeneous feature spaces via feature-space remapping (FSR). J ACM Trans Intell Syst Technol. 2014;6(1):1–27.

    Article  Google Scholar 

  20. Huang J, Smola A, Gretton A, Borgwardt KM, Schölkopf B. Correcting sample selection bias by unlabeled data. In: Proceedings of the 2006 conference in advances in neural information processing systems; 2006. p. 601–8.

    Google Scholar 

  21. Jiang J, Zhai C. Instance weighting for domain adaptation in NLP. In: Proceedings of the 45th annual meeting of the association of computational linguistics; 2007. p. 264–271.

    Google Scholar 

  22. Pan SJ, Kwok JT, Yang Q. Transfer learning via dimensionality reduction. In: Proceedings of the 23rd national conference on artificial intelligence, vol. 2; 2008. p. 677–82.

    Google Scholar 

  23. Gao J, Fan W, Jiang J, Han J. Knowledge transfer via multiple model local structure mapping. In: Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining; 2008. p. 283–91.

    Google Scholar 

  24. Bonilla E, Chai KM, Williams C. Multi-task Gaussian process prediction. In: Proceedings of the 20th annual conference of neural information processing systems; 2008. p. 153–60.

    Google Scholar 

  25. Evgeniou T, Pontil M. Regularized multi-task learning. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining; 2004. p. 109–17.

    Google Scholar 

  26. Mihalkova L, Mooney RJ. Transfer learning by mapping with minimal target data. In: Proceedings of the association for the advancement of artificial intelligence workshop transfer learning for complex tasks; 2008. p. 31–6.

    Google Scholar 

  27. Li F, Pan SJ, Jin O, Yang Q, Zhu X. Cross-domain co-extraction of sentiment and topic lexicons. In: Proceedings of the 50th annual meeting of the association for computational linguistics long papers, vol. 1; 2012. p. 410–9.

    Google Scholar 

  28. Duan L, Tsang IW, Xu D. Domain transfer multiple kernel learning. IEEE Trans Pattern Anal Mach Intell. 2012;34(3):465–79.

    Article  Google Scholar 

  29. Long M, Wang J, Ding G, Sun J, Yu PS. Transfer feature learning with joint distribution adaptation. In: Proceedings of the 2013 IEEE international conference on computer vision; 2013. p. 2200–7.

    Google Scholar 

  30. Long M, Wang J, Ding G, Pan SJ, Yu PS. Adaptation regularization: a general framework for transfer learning. IEEE Trans Knowl Data Eng. 2014;26(5):1076–89.

    Article  Google Scholar 

  31. Pan SJ, Tsang IW, Kwok JT, Yang Q. Domain adaptation via transfer component analysis. IEEE Trans Neural Netw. 2009;22(2):199–210.

    Article  Google Scholar 

  32. Pan SJ, Ni X, Sun JT, Yang Q, Chen Z. Cross-domain sentiment classification via spectral feature alignment. In: Proceedings of the 19th international conference on world wide web; 2010. p. 751–60.

    Google Scholar 

  33. Glorot X, Bordes A, Bengio Y. Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the twenty-eight international conference on machine learning, vol. 27; 2011. p. 97–110.

    Google Scholar 

  34. Shi Y, Sha F. Information-theoretical learning of discriminative clusters for unsupervised domain adaptation. In: Proceedings of the 29th international conference on machine learning; 2012. p. 1–8.

    Google Scholar 

  35. Oquab M, Bottou L, Laptev I, Sivic J. Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition; 2013. p. 1717–24.

    Google Scholar 

  36. Tommasi T, Orabona F, Caputo B. Safety in numbers: learning categories from few examples with multi model knowledge transfer. In: 2010 IEEE conference on computer vision and pattern recognition; 2010. p. 3081–8.

    Google Scholar 

  37. Duan L, Xu D, Chang SF. Exploiting web images for event recognition in consumer videos: a multiple source domain adaptation approach. In: IEEE 2012 conference on computer vision and pattern recognition; 2012. p. 1338–45.

    Google Scholar 

  38. Yao Y, Doretto G. Boosting for transfer learning with multiple sources. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition; 2010. p. 1855–62.

    Google Scholar 

  39. Xia R, Zong C, Hu X, Cambria E. Feature ensemble plus sample selection: Domain adaptation for sentiment classification. IEEE Intell Syst. 2013;28(3):10–8.

    Article  Google Scholar 

  40. Duan L, Xu D, Tsang IW. Domain adaptation from multiple sources: a domain-dependent regularization approach. IEEE Trans Neural Netw Learn Syst. 2012;23(3):504–18.

    Article  Google Scholar 

  41. Zhong E, Fan W, Peng J, Zhang K, Ren J, Turaga D, Verscheure O. Cross domain distribution adaptation via kernel mapping. In: Proceedings of the 15th ACM SIGKDD; 2009. p 1027–36.

    Google Scholar 

  42. Chelba C, Acero A. Adaptation of maximum entropy classifier: little data can help a lot. Comput Speech Lang. 2004;20(4):382–99.

    Article  Google Scholar 

  43. Wu X, Xu D, Duan L, Luo J. Action recognition using context and appearance distribution features. In: IEEE 2011 conference on computer vision and pattern recognition; 2011. p. 489–96.

    Google Scholar 

  44. Vedaldi A, Gulshan V, Varma M, Zisserman A. Multiple kernels for object detection. In: 2009 IEEE 12th international conference on computer vision; 2009. p. 606–13.

    Google Scholar 

  45. Vapnik V. Principles of risk minimization for learning theory. Adv Neural Inf Process Syst. 1992;4:831–8.

    Google Scholar 

  46. Borgwardt KM, Gretton A, Rasch MJ, Kriegel HP, Schölkopf B, Smola AJ. Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics. 2006;22(4):49–57.

    Article  Google Scholar 

  47. Yang J, Yan R, Hauptmann AG. Cross-domain video concept detection using adaptive SVMs. In: Proceedings of the 15th ACM international conference on multimedia; 2007. p. 188–97.

    Google Scholar 

  48. Jiang W, Zavesky E, Chang SF, Loui A. Cross-domain learning methods for high-level visual concept classification. In: IEEE 2008 15th international conference on image processing; 2008. p. 161–4.

    Google Scholar 

  49. Si S, Tao D, Geng B. Bregman divergence-based regularization for transfer subspace learning. IEEE Trans Knowl Data Eng. 2010;22(7):929–42.

    Article  Google Scholar 

  50. Belkin M, Niyogi P, Sindhwani V. Manifold regularization: a geometric framework for learning from examples. J Mach Learn Res Arch. 2006;7:2399–434.

    MathSciNet  MATH  Google Scholar 

  51. Ling X, Dai W, Xue GR, Yang Q, Yu Y. Spectral domain-transfer learning. In: Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining; 2008. p. 488–96.

    Google Scholar 

  52. Quanz B, Huan J. Large margin transductive transfer learning. In: Proceedings of the 18th ACM conference on information and knowledge management; 2009. p. 1327–36.

    Google Scholar 

  53. Xiao M, Guo Y. Semi-supervised kernel matching for domain adaptation. In: Proceedings of the twenty-sixth AAAI conference on artificial intelligence; 2012. p. 1183–89.

    Google Scholar 

  54. Steinwart I. On the influence of the kernel on the consistency of support vector machines. JMLR. 2001;2:67–93.

    MathSciNet  MATH  Google Scholar 

  55. Chung FRK. Spectral graph theory. In: Number 92 in CBMS regional conference series in mathematics. American Mathematical Society, Published by AMS; 1994.

    Google Scholar 

  56. Vincent P, Larochelle H, Bengio Y, Manzagol PA. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning; 2008. p. 1096–103.

    Google Scholar 

  57. Li S, Zong C. Multi-domain adaptation for sentiment classification: using multiple classifier combining methods. In: Proceedings of the conference on natural language processing and knowledge engineering; 2008. p. 1–8.

    Google Scholar 

  58. Gopalan R, Li R, Chellappa R. Domain adaptation for object recognition: an unsupervised approach. Int Conf Comput Vis. 2011;2011:999–1006.

    Google Scholar 

  59. Weinberger KQ, Saul LK. Distance metric learning for large margin nearest neighbor classification. JMLR. 2009;10:207–44.

    MATH  Google Scholar 

  60. LeCun Y, Bottou L, HuangFu J. Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition; 2004, vol. 2, p. 97–104.

    Google Scholar 

  61. Marszalek M, Schmid C, Harzallah H, Van de Weijer J. Learning object representations for visual object class recognition. In: Visual recognition challenge workshop ICCV; 2007. p. 1–10.

    Google Scholar 

  62. Song Z, Chen Q, Huang Z, Hua Y, Yan S. Contextualizing object detection and classification. IEEE Trans Pattern Anal Mach Intell. 2011;37(1):13–27.

    Google Scholar 

  63. Cawley G. Leave-one-out cross-validation based model selection criteria for weighted LS-SVMs. In: IEEE 2006 international joint conference on neural network proceedings; 2006. p. 1661–68.

    Google Scholar 

  64. Tommasi T, Caputo B. The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories. In: BMVC; 2009. p. 1–11.

    Google Scholar 

  65. Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vision. 2004;60(2):91–110.

    Article  Google Scholar 

  66. Wang H, Klaser A, Schmid C, Liu CL. Action recognition by dense trajectories. In: IEEE 2011 conference on computer vision and pattern recognition; 2011. p. 3169–76.

    Google Scholar 

  67. Bruzzone L, Marconcini M. Domain adaptation problems: a DASVM classification technique and a circular validation strategy. IEEE Trans Pattern Anal Mach Intell. 2010;32(5):770–87.

    Article  Google Scholar 

  68. Schweikert G, Widmer C, Schölkopf B, Rätsch G. An empirical analysis of domain adaptation algorithms for genomic sequence analysis. Adv Neural Inf Process Syst. 2009;21:1433–40.

    Google Scholar 

  69. Dai W, Yang Q, Xue GR, Yu Y. Boosting for transfer learning. In: Proceedings of the 24th international conference on Machine learning; 2007. p. 193–200.

    Google Scholar 

  70. Hu M, Liu B. Mining and summarizing customer reviews. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining; 2004. p. 168–77.

    Google Scholar 

  71. Qiu G, Liu B, Bu J, Chen C. Expanding domain sentiment lexicon through double propagation. In: Proceedings of the 21st international joint conference on artificial intelligence; 2009. p. 1199–204.

    Google Scholar 

  72. Jakob N, Gurevych I. Extracting opinion targets in a single and cross-domain setting with conditional random fields. In: Proceedings of the 2010 conference on empirical methods in NLP; 2010. p. 1035–45.

    Google Scholar 

  73. Xia R, Zong C. A POS-based ensemble model for cross-domain sentiment classification. In: Proceedings of the 5th international joint conference on natural language processing; 2011. p. 614–622.

    Google Scholar 

  74. Shi X, Liu Q, Fan W, Yu PS, Zhu R. Transfer learning on heterogeneous feature spaces via spectral transformation. IEEE Int Conf Data Mining. 2010;2010:1049–54.

    Google Scholar 

  75. Qi GJ, Aggarwal C, Huang T. Towards semantic knowledge propagation from text corpus to web images. In: Proceedings of the 20th international conference on world wide web; 2011. p. 297–306.

    Google Scholar 

  76. Li W, Duan L, Xu D, Tsang IW. Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans Pattern Anal Mach Intell. 2014;36(6):1134–48.

    Article  Google Scholar 

  77. Wei B, Pal C. Heterogeneous transfer learning with RBMs. In: Proceedings of the twenty-fifth AAAI conference on artificial intelligence; 2011. p. 531–36.

    Google Scholar 

  78. Ham JH, Lee DD, Saul LK. Learning high dimensional correspondences from low dimensional manifolds. In: Proceedings of the twentieth international conference on machine learning; 2003. p. 1–8.

    Google Scholar 

  79. Yang Q, Chen Y, Xue GR, Dai W, Yu Y. Heterogeneous transfer learning for image clustering via the social web. In: Proceedings of the joint conference of the 47th annual meeting of the ACL; 2009, vol. 1. p. 1–9.

    Google Scholar 

  80. Deerwester S, Dumais ST, Furnas GW, Landauer TK, Harshman R. Indexing by latent semantic analysis. J Am Soc Inf Sci. 1990;41:391–407.

    Article  Google Scholar 

  81. Raina R, Battle A, Lee H, Packer B, Ng AY. Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th international conference on machine learning; 2007. p. 759–66.

    Google Scholar 

  82. Wang G, Hoiem D, Forsyth DA. Building text Features for object image classification. IEEE Conf Comput Vis Pattern Recognit. 2009;2009:1367–74.

    Google Scholar 

  83. Dai W, Chen Y, Xue GR, Yang Q, Yu Y. Translated learning: transfer learning across different feature spaces. Adv Neural Inf Process Syst. 2008;21:353–60.

    Google Scholar 

  84. Bay H, Tuytelaars T, Gool LV. Surf: speeded up robust features. Comput Vis Image Underst. 2006;110(3):346–59.

    Article  Google Scholar 

  85. Kloft M, Brefeld U, Sonnenburg S, Zien A. Lp-norm multiple kernel learning. J Mach Learn Res. 2011;12:953–97.

    MathSciNet  MATH  Google Scholar 

  86. Shawe-Taylor J, Cristianini N. Kernel methods for pattern analysis. Cambridge: Cambridge University Press; 2004.

    Book  MATH  Google Scholar 

  87. Davis J, Kulis B, Jain P, Sra S, Dhillon I. Information theoretic metric learning. In: Proceedings of the 24th international conference on machine learning; 2007. p. 209–16.

    Google Scholar 

  88. Saenko K, Kulis B, Fritz M, Darrell T. Adapting visual category models to new domains. Comput Vis ECCV. 2010;6314:213–26.

    Google Scholar 

  89. Ando RK, Zhang T. A framework for learning predictive structures from multiple tasks and unlabeled data. J Mach Learn Res. 2005;6:1817–53.

    MathSciNet  MATH  Google Scholar 

  90. Gao K, Khoshgoftaar TM, Wang H, Seliya N. Choosing software metrics for defect prediction: an investigation on feature selection techniques. J Softw Pract Exp. 2011;41(5):579–606.

    Article  Google Scholar 

  91. Shivaji S, Whitehead EJ, Akella R, Kim S. Reducing features to improve code change-based bug prediction. IEEE Trans Software Eng. 2013;39(4):552–69.

    Article  Google Scholar 

  92. He P, Li B, Ma Y. Towards cross-project defect prediction with imbalanced feature sets; 2014. arXiv preprint arXiv:1411.4228.

  93. Chen M, Xu ZE, Weinberger KQ, Sha F. Marginalized denoising autoencoders for domain adaptation. ICML; 2012. arXiv preprint arXiv:1206.4683.

  94. Vinokourov A, Shawe-Taylor J, Cristianini N. Inferring a semantic representation of text via crosslanguage correlation analysis. Adv Neural Inf Process Syst. 2002;15:1473–80.

    Google Scholar 

  95. Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY. Multimodal deep learning. In: The 28th International conference on machine learning; 2011. p. 689–96.

    Google Scholar 

  96. Yang L, Jing L, Yu J, Ng MK. Learning transferred weights from co-occurrence data for heterogeneous transfer learning. In: IEEE transaction on neural networks and learning systems; 2015. p. 1–14.

    Google Scholar 

  97. Ng MK, Wu Q, Ye Y. Co-transfer learning via joint transition probability graph based method. In: Proceedings of the 1st international workshop on cross domain knowledge discovery in web and social network mining; 2012. p. 1–9.

    Google Scholar 

  98. Rosenstein MT, Marx Z, Kaelbling LP, Dietterich TG. To transfer or not to transfer. In: Proceedings NIPS’05 workshop, inductive transfer, 10 years later; 2005. p. 1–4.

    Google Scholar 

  99. Eaton E, desJardins M, Lane R. Modeling transfer relationships between learning tasks for improved inductive transfer. Proc Mach Learn Knowl Discov Databases. 2008;5211:317–32.

    Article  Google Scholar 

  100. Ge L, Gao J, Ngo H, Li K, Zhang A. On handling negative transfer and imbalanced distributions in multiple source transfer learning. In: Proceedings of the 2013 SIAM international conference on data mining; 2013. p. 254–71.

    Google Scholar 

  101. Luo P, Zhuang F, Xiong H, Xiong Y, He Q. Transfer learning from multiple source domains via consensus regularization. In: Proceedings of the 17th ACM conference on information and knowledge management; 2008. p. 103–12.

    Google Scholar 

  102. Gao J, Liang F, Fan W, Sun Y, Han J. Graph based consensus maximization among multiple supervised and unsupervised models. Adv Neural Inf Process Syst. 2009;22:1–9.

    Google Scholar 

  103. Seah CW, Ong YS, Tsang IW. Combating negative transfer from predictive distribution differences. IEEE Trans Cybern. 2013;43(4):1153–65.

    Article  Google Scholar 

  104. Moreno O, Shapira B, Rokach L, Shani G. TALMUD—transfer learning for multiple domains. In: Proceedings of the 21st ACM international conference on Information and knowledge management; 2012. p. 425–34.

    Google Scholar 

  105. Cao B, Liu N, Yang Q. Transfer learning for collective link prediction in multiple heterogeneous domains. In: Proceedings of the 27th international conference on machine learning; 2010. p. 159–66.

    Google Scholar 

  106. Li B, Yang Q, Xue X. Can movies and books collaborate? Cross-domain collaborative filtering for sparsity reduction. In: Proceedings of the 21st international joint conference on artificial intelligence; 2009. p. 2052–57.

    Google Scholar 

  107. Li B, Yang Q, Xue X. Transfer learning for collaborative filtering via a rating-matrix generative model. In: Proceedings of the 26th annual international conference on machine learning; 2009. p. 617–24.

    Google Scholar 

  108. Pan W. Xiang EW, Liu NN, Yang Q. Transfer learning in collaborative filtering for sparsity reduction. In: Twenty-fourth AAAI conference on artificial intelligence, vol. 1; 2010. p. 230–5.

    Google Scholar 

  109. Zhang Y, Cao B, Yeung D. Multi-domain collaborative filtering. In: Proceedings of the 26th conference on uncertainty in artificial intelligence; 2010. p. 725–32.

    Google Scholar 

  110. Pan W, Liu NN, Xiang EW, Yang Q. Transfer learning to predict missing ratings via heterogeneous user feedbacks. In: Proceedings of the 22nd international joint conference on artificial intelligence; 2011. p. 2318–23.

    Google Scholar 

  111. Roy SD, Mei T, Zeng W, Li S. Social transfer: cross-domain transfer learning from social streams for media applications. In: Proceedings of the 20th ACM international conference on multimedia; 2012. p. 649–58.

    Google Scholar 

  112. Jiang M, Cui P, Wang F, Yang Q, Zhu W, Yang S. Social recommendation across multiple relational domains. In: Proceedings of the 21st ACM international conference on information and knowledge management; 2012. p. 1422–31.

    Google Scholar 

  113. Zhao L, Pan SJ, Xiang EW, Zhong E, Lu Z, Yang Q. Active transfer learning for cross-system recommendation. In: Proceedings of the 27th AAAI conference on artificial intelligence; 2013. p. 1205–11.

    Google Scholar 

  114. Rajagopal AN, Subramanian R, Ricci E, Vieriu RL, Lanz O, Ramakrishnan KR, Sebe N. Exploring transfer learning approaches for head pose classification from multi-view surveillance images. Int J Comput Vision. 2014;109(1–2):146–67.

    Article  Google Scholar 

  115. Ma Y, Gong W, Mao F. Transfer learning used to analyze the dynamic evolution of the dust aerosol. J Quant Spectrosc Radiat Transfer. 2015;153:119–30.

    Article  Google Scholar 

  116. Xie M, Jean N, Burke M, Lobell D, Ermon S. Transfer learning from deep features for remote sensing and poverty mapping. In: Proceedings 30th AAAI conference on artificial intelligence; 2015. p. 1–10.

    Google Scholar 

  117. Ogoe HA, Visweswaran S, Lu X, Gopalakrishnan V. Knowledge transfer via classification rules using functional mapping for integrative modeling of gene expression data. BMC Bioinformatics. 2015;16:1–15.

    Article  Google Scholar 

  118. Perlich C, Dalessandro B, Raeder T, Stitelman O, Provost F. Machine learning for targeted display advertising: transfer learning in action. Mach Learn. 2014;95:103–27.

    Article  MathSciNet  Google Scholar 

  119. Kan M, Wu J, Shan S, Chen X. Domain adaptation for face recognition: targetize source domain bridged by common subspace. Int J Comput Vis. 2014;109(1–2):94–109.

    Article  MATH  Google Scholar 

  120. Farhadi A, Forsyth D, White R. Transfer learning in sign language. In: IEEE 2007 conference on computer vision and pattern recognition; 2007. p. 1–8.

    Google Scholar 

  121. Widmer C, Ratsch G. Multitask learning in computational biology. JMLR. 2012;27:207–16.

    Google Scholar 

  122. Wiens J, Guttag J, Horvitz EJ. A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions. J Am Med Inform Assoc. 2013;21(4):699–706.

    Article  Google Scholar 

  123. Romera-Paredes B, Aung MSH, Pontil M, Bianchi-Berthouze N, Williams AC de C, Watson P. Transfer learning to account for idiosyncrasy in face and body expressions. In: Proceedings of the 10th international conference on automatic face and gesture recognition (FG); 2013. p. 1–6.

    Google Scholar 

  124. Deng J, Zhang Z, Marchi E, Schuller B. Sparse autoencoder based feature transfer learning for speech emotion recognition. In: Humaine association conference on affective computing and intelligent interaction; 2013. p. 511–6.

    Google Scholar 

  125. Zhang Y, Yeung DY. Transfer metric learning by learning task relationships. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining; 2010. p. 1199–208.

    Google Scholar 

  126. Patel VM, Gopalan R, Li R, Chellappa R. Visual domain adaptation: a survey of recent advances. IEEE Signal Process Mag. 2014;32(3):53–69.

    Article  Google Scholar 

  127. Shao L, Zhu F, Li X. Transfer learning for visual categorization: a survey. IEEE Trans Neural Netw Learn Syst. 2014;26(5):1019–34.

    Article  MathSciNet  Google Scholar 

  128. Bolt Online Learning Toolbox. http://pprett.github.com/bolt/. Accessed 4 Mar 2016.

  129. Zhu Y. http://www.cse.ust.hk/~yinz/. Accessed 4 Mar 2016.

  130. BoChen90 Update TrAdaBoost.m. https://github.com/BoChen90/machine-learning-matlab/blob/master/TrAdaBoost.m. Accessed 4 Mar 2016.

  131. EasyAdapt.pl.gz (Download). http://hal3.name/easyadapt.pl.gz Accessed 4 Mar 2016.

  132. HFA_release_0315.rar (Download). https://sites.google.com/site/xyzliwen/publications/HFA_release_0315.rar. Accessed 4 Mar 2016.

  133. Computer Vision and Learning Group. http://vision.cs.uml.edu/adaptation.html. Accessed 4 Mar 2016.

  134. Guo-Jun Qi’s Publication List. http://www.eecs.ucf.edu/~gqi/publications.html. Accessed 4 Mar 2016.

  135. Duan L. http://www.lxduan.info/#sourcecode_hfa. Accessed 4 Mar 2016.

  136. Gong B. http://www-scf.usc.edu/~boqinggo/. Accessed 4 Mar 2016.

  137. Long MS—Tsinghua University. http://ise.thss.tsinghua.edu.cn/~mlong/. Accessed 4 Mar 2016.

  138. Papers:oquab-2014. http://leon.bottou.org/papers/oquab-2014. Accessed 4 Mar 2016.

  139. Transfer Learning Resources. http://www.cse.ust.hk/TL/. Accessed 4 Mar 2016.

  140. Heterogeneous Defect Prediction. http://www.slideshare.net/hunkim/heterogeneous-defect-prediction-esecfse-2015. Accessed 4 Mar 2016.

  141. LIBSVM—A library for support vector machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm. Accessed 4 Mar 2016.

  142. Domain Adaptation Project. https://www.eecs.berkeley.edu/~jhoffman/domainadapt/. Accessed 4 Mar 2016.

  143. Tutorial on domain adaptation and transfer learning. http://tommasit.wix.com/datl14tutorial. Accessed 4 Mar 2016.

  144. A literature survey on domain adaptation of statistical classifiers. http://sifaka.cs.uiuc.edu/jiang4/domain_adaptation/survey/da_survey.html. Accessed 4 Mar 2016.

  145. Exploiting web images for event recognition in consumer videos: a multiple source domain adaptation approach. http://lxduan.info/papers/DuanCVPR2012_poster.pdf. Accessed 4 Mar 2016.

Download references

Author information

Authors and Affiliations

  1. Florida Atlantic University, Boca Raton, FL, USA

    Karl Weiss, Taghi M. Khoshgoftaar & DingDing Wang

Authors
  1. Karl Weiss
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Taghi M. Khoshgoftaar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. DingDing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Appendix

Appendix

The majority of transfer learning solutions surveyed are complex and implemented with non-trivial software. It is a great advantage for a researcher to have access to software implementations of transfer learning solutions so comparisons with competing solutions are facilitated more quickly and fairly. Table 3.5 provides a list of available software downloads for a number of the solutions surveyed in this paper. Table 3.6 provides a resource for useful links that point to transfer learning tutorials and other interesting articles on the topic of transfer learning.

Table 3.5 Software downloads for various transfer learning solutions
Full size table
Table 3.6 Useful links for transfer learning information
Full size table

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Weiss, K., Khoshgoftaar, T.M., Wang, D. (2016). Transfer Learning Techniques. In: Big Data Technologies and Applications. Springer, Cham. https://doi.org/10.1007/978-3-319-44550-2_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-44550-2_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-44548-9

  • Online ISBN: 978-3-319-44550-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation