Advertisement

Query by diverse committee in transfer active learning

  • Hao Shao
Research Artice
  • 15 Downloads

Abstract

Transfer active learning, which is an emerging learning paradigm, aims to actively select informative instances with the aid of transferred knowledge from related tasks. Recently, several studies have addressed this problem. However, how to handle the distributional differences between the source and target domains remains an open problem. In this paper, a novel transfer active learning algorithm is proposed, inspired by the classical query by committee algorithm. Diverse committee members from both domains are maintained to improve the classification accuracy and a mechanism is included to evaluate each member during the iterations. Extensive experiments on both synthetic and real datasets show that our algorithm performs better and is also more robust than the state-of-the-art methods.

Keywords

transfer learning active learning machine learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was supported by the Humanity and Social Science Youth Foundation of the Ministry of Education of China (13YJC630126), SRF for ROCS, SEM, SC-GTEG, the National Natural Science Foundations of China (NSFC) (Grant Nos. 61603240, 71171184, 71201059, and 71201151), the Funds for Creative Research Group of China (70821001), and the Major Program of NSFC (71090401 and 71090400).

Supplementary material

11704_2017_6117_MOESM1_ESM.ppt (267 kb)
Supplementary material, approximately 267 KB.

References

  1. 1.
    Settles B. Active learning literature survey. Technical Report No. 1648, 2010Google Scholar
  2. 2.
    Rosenstein M T, Z. Marx L P K, Dietterich T G. To transfer or not to transfer. In: Proceedings of NIPS Workshop on Transfer Learning, 2005Google Scholar
  3. 3.
    Houlsby N, Lobato J M H, Ghahramani Z. Cold-start active learning with robust ordinal matrix factorization. In: Proceedings of the 31st International Conference of Machine Learning. 2014, 766–774Google Scholar
  4. 4.
    Shao H, Tong B, Suzuki E. Query by committee in a heterogeneous environment. In: Proceedings of the 8th International Conference on Advanced Data Mining and Applications. 2012, 186–198CrossRefGoogle Scholar
  5. 5.
    Kale D, Liu Y. Accelerating active learning with transfer learning. In: Proceedings of the 13th IEEE International Conference on Data Mining. 2013, 1085–1090Google Scholar
  6. 6.
    Chattopadhyay R, Fan W, Davidson I, Panchanathan S, Ye J. Joint transfer and batch-mode active learning. In: Proceedings of the 30th International Conference on Machine Learning. 2013, 253–261Google Scholar
  7. 7.
    Zhu Z, Zhu X, Ye Y, Guo Y F, Xue X. Transfer active learning. In: Proceedings of the 20th International Conference on Information and Knowledge Management. 2011, 2169–2172Google Scholar
  8. 8.
    Rai P, Saha A, Daumé III H, Venkatasubramanian S. Domain adaptation meets active learning. In: Proceedings of the NAACL HLT Workshop on Active Learning for Natural Language Processing. 2010, 27–32Google Scholar
  9. 9.
    Fang M, Yin J, Zhu X. Knowledge transfer for multi-labeler active learning. In: Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. 2013, 273–288CrossRefGoogle Scholar
  10. 10.
    Li H, Shi Y, Chen M, Hauptmann A G, Xiong Z. Hybrid active learning for cross-domain video concept detection. In: Proceedings of the 18th ACM International Conference on Multimedia. 2010, 1003–1006Google Scholar
  11. 11.
    Shi X, FanW, Ren J. Actively transfer domain knowledge. In: Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. 2008, 342–357CrossRefGoogle Scholar
  12. 12.
    Luo C, Ji Y, Dai X, Chen J. Active learning with transfer learning. In: Proceedings of ACL Student Research Workshop. 2012, 13–18Google Scholar
  13. 13.
    Yang L, Hanneke S, Carbonell J. A theory of transfer learning with applications to active learning. Maching Learning, 2013, 90(2): 161–189MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Caruana R. Multitask learning. In: Thrun S, Pratt L, eds. Leaning to Learn. Springer US, 1998, 95–133Google Scholar
  15. 15.
    Shao H, Suzuki E. Feature-based inductive transfer learning through minimum encoding. In: Proceedings of the SIAM International Conference on Data Mining. 2011, 259–270Google Scholar
  16. 16.
    Reichart R, Tomanek K, Hahn U, Rappoport A. Multi-task active learning for linguistic annotations. In: Proceedings of Annual Meeting of the Association for Computational Linguistics. 2008, 861–869Google Scholar
  17. 17.
    Raj S, Ghosh J, Crawford M M. An active learning approach to knowledge transfer for hyperspectral data analysis. In: Proceedings of IEEE International Conference on Geoscience and Remote Sensing Symposium. 2006, 541–544Google Scholar
  18. 18.
    Roy N, Mccallum A. Toward optimal active learning through sampling estimation of error reduction. In: Proceedings of the 18th International Conference on Machine Learning. 2011, 441–448Google Scholar
  19. 19.
    Huang S J, Chen S. Transfer learning with active queries from source domain. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2016, 1592–1598Google Scholar
  20. 20.
    Gao N, Huang S J, Chen S. Multi-label active learning by model guided distribution matching. Frontiers of Computer Science, 2016, 10(5): 845–855CrossRefGoogle Scholar
  21. 21.
    Wallace C, Patrick J. Coding decision trees. Journal of Machine Learning, 1993, 11(1): 7–22CrossRefMATHGoogle Scholar
  22. 22.
    Quinlan J R, Rivest R L. Inferring decision trees using the minimumdescription length principle. Information and Computation, 1989, 80(3): 227–248MathSciNetCrossRefMATHGoogle Scholar
  23. 23.
    Shannon C E. A mathematical theory of communication. Bell System Technical Journal, 1948, 27: 379–423MathSciNetCrossRefMATHGoogle Scholar
  24. 24.
    Dagan I, Engelson S P. Committee-based sampling for training probabilistic classifiers. In: Proceedings of the 23rd International Conference on Machine Learning. 2006, 150–157Google Scholar
  25. 25.
    Lewis D D, Gale W A. A sequential algorithm for training text classifiers. In: Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval. 1994, 3–12Google Scholar
  26. 26.
    Krause A, Guestrin C. Optimal value of information in graphical models. Journal of Artificial Intelligence, 2009, 35: 557–591MathSciNetMATHGoogle Scholar
  27. 27.
    Zhang Y. Multi-task active learning with output constraints. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence. 2010Google Scholar
  28. 28.
    Seung H S, Opper M, Sompolinsky H. Query by committee. In: Proceedings of the 5th Annud workshop on Computational Learning Theory. 1992, 287–294Google Scholar
  29. 29.
    McCallum A, Nigam K. Employing em in pool-based active learning for text classification. In: Proceedings of the 15th International Conference of Machine Learning. 1998, 350–358Google Scholar
  30. 30.
    Balcan M F, Beygelzimer A, Langford J. Agnostic active learning. In: Proceedings of the 23rd International Conference on Machine Learning. 2006, 65–72Google Scholar
  31. 31.
    Chang C C, Lin C J. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2001, 2(3): 1–27CrossRefGoogle Scholar
  32. 32.
    Dai W, Yang Q, Xue G R, Yu Y. Boosting for transfer learning. In: Proceedings of the 24th International Conference of Machine Learning. 2007, 193–200Google Scholar
  33. 33.
    Shi Y, Lan Z, Liu W, Bi W. Extending semi-supervised learning methods for inductive transfer learning. In: Proceedings of IEEE International Conference on Data Mining. 2009, 483–492Google Scholar

Copyright information

© Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.WTO SchoolShanghai University of International Business and EconomicsShanghaiChina

Personalised recommendations