ABSTRACT
Traditional spectral classification has been proved to be effective in dealing with both labeled and unlabeled data when these data are from the same domain. In many real world applications, however, we wish to make use of the labeled data from one domain (called in-domain) to classify the unlabeled data in a different domain (out-of-domain). This problem often happens when obtaining labeled data in one domain is difficult while there are plenty of labeled data from a related but different domain. In general, this is a transfer learning problem where we wish to classify the unlabeled data through the labeled data even though these data are not from the same domain. In this paper, we formulate this domain-transfer learning problem under a novel spectral classification framework, where the objective function is introduced to seek consistency between the in-domain supervision and the out-of-domain intrinsic structure. Through optimization of the cost function, the label information from the in-domain data is effectively transferred to help classify the unlabeled data from the out-of-domain. We conduct extensive experiments to evaluate our method and show that our algorithm achieves significant improvements on classification performance over many state-of-the-art algorithms.
- S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira. Analysis of representations for domain adaptation. In NIPS, 2007.Google ScholarDigital Library
- S. Ben-David and R. Schuller. Exploiting task relatedness for multiple task learning. In COLT, 2003.Google Scholar
- S. Bickel, M. Brückner, and T. Scheffer. Discriminative learning for differing training and test distributions. In ICML, 2007. Google ScholarDigital Library
- S. Bickel and T. Scheffer. Dirichlet-enhanced spam filtering based on biased samples. In NIPS, 2007.Google ScholarDigital Library
- J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. Wortman. Learning bounds for domain adaptation. In NIPS, 2008.Google ScholarDigital Library
- J. Blitzer, R. McDonald, and F. Pereira. Domain adaptation with structural correspondence learning. In EMNLP, 2006. Google ScholarDigital Library
- R. Caruana. Multitask Learning. Machine Learning, 28(1):41--75, 1997. Google ScholarDigital Library
- C.-K. Cheng and Y.-C. A. Wei. An improved two-way partitioning algorithm with stable performance {VLSI}. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 10(12):1502--1511, 1991.Google ScholarDigital Library
- F. R. K. Chung. Spectral Graph Theory. American Mathematical Society, 1997.Google Scholar
- W. Dai, G.-R. Xue, Q. Yang, and Y. Yu. Co-clustering based classification for out-of-domain documents. In SIGKDD, 2007. Google ScholarDigital Library
- W. Dai, G.-R. Xue, Q. Yang, and Y. Yu. Transferring naive bayes classifiers for text classification. In AAAI, 2007. Google ScholarDigital Library
- W. Dai, Q. Yang, G.-R. Xue, and Y. Yu. Boosting for transfer learning. In ICML, 2007. Google ScholarDigital Library
- H. Daum2e III. Frustratingly easy domain adaptation. In ACL, 2007.Google Scholar
- H. Daume III and D. Marcu. Domain adaptation for statistical classifiers. JAIR, 1:1--15, 2006. Google ScholarDigital Library
- C. Ding, X. He, H. Zha, M. Gu, and H. Simon. Spectral min-max cut for graph partitioning and data clustering. In ICDM, 2001. Google ScholarDigital Library
- G. H. Golub and C. F. Van Loan. Matrix Computation. The Johns Hopkins University Press Baltimore, 1996.Google Scholar
- J. J. Heckman. Sample selection bias as a specification error. Econometrica, 47(1):153--162, 1979.Google ScholarCross Ref
- J. Huang, A. J. Smola, A. Gretton, K. Borgwardt, and B. Schölkopf. Correcting sample selection bias by unlabeled data. In NIPS, 2007.Google ScholarDigital Library
- X. Ji and W. Xu. Document clustering with prior knowledge. In SIGIR, 2006. Google ScholarDigital Library
- T. Joachims. Transductive inference for text classification using support vector machines. In ICML,1999. Google ScholarDigital Library
- T. Joachims. Transductive learning via spectral graph partitioning. In ICML, 2003.Google ScholarDigital Library
- S. D. Kamvar, D. Klein, and C. D. Manning. Spectral learning. In IJCAI, 2003. Google ScholarDigital Library
- X. Liao, Y. Xue, and L. Carin. Logistic regression with an auxiliary data source. In ICML, 2005. Google ScholarDigital Library
- M. Meila and J. Shi. A random walks view of spectral segmentation. In Proceedings of the 8th International Workshop on Artificial Intelligence and Statistics, 2001.Google Scholar
- A. Y. Ng, M. I. Jordan, and Y. Weiss. On spectral clustering: Analysis and an algorithm. In NIPS, 2001.Google ScholarDigital Library
- M. Porter. An algorithm for suffix stripping program. Program, 14(3):130--137, 1980.Google ScholarCross Ref
- J. Schmidhuber. On learning how to learn learning strategies. Technical Report FKI-198-94, Fakultat fur Informatik, 1994.Google Scholar
- J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):888--905, 2000. Google ScholarDigital Library
- H. Shimodaira. Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2):227--244, 2000.Google ScholarCross Ref
- S. Thrun and T. Mitchell. Learning one more thing. In IJCAI, 1995. Google ScholarDigital Library
- K. Wagstaff and C. Cardie. Clustering with instance-level constraints. In ICML, 2000. Google ScholarDigital Library
- P. Wu and T. G. Dietterich. Improving SVM accuracy by training on auxiliary data sources. In ICML, 2004. Google ScholarDigital Library
- D. Xing, W. Dai, G.-R. Xue, and Y. Yu. Bridged refinement for transfer learning. In PKDD, 2007.Google ScholarCross Ref
- Y. Yang and J. O. Pedersen. A comparative study on feature selection in text categorization. In ICML, 1997. Google ScholarDigital Library
- B. Zadrozny. Learning and evaluating classifiers under sample selection bias. In ICML, 2004. Google ScholarDigital Library
Index Terms
- Spectral domain-transfer learning
Recommendations
A robust semi-supervised classification method for transfer learning
CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge managementThe transfer learning problem of designing good classifiers with a high generalization ability by using labeled samples whose distribution is different from that of test samples is an important and challenging research issue in the fields of machine ...
Transfer active learning
CIKM '11: Proceedings of the 20th ACM international conference on Information and knowledge managementActive learning traditionally assumes that labeled and unlabeled samples are subject to the same distributions and the goal of an active learner is to label the most informative unlabeled samples. In reality, situations may exist that we may not have ...
A Tri-training Based Transfer Learning Algorithm
ICTAI '12: Proceedings of the 2012 IEEE 24th International Conference on Tools with Artificial Intelligence - Volume 01The lack of labeled training data is a common issue in many machine learning applications. Semi-supervised learning addresses this issue by self-labeling unlabelled examples. Transfer learning tackles it from a different way: borrow labeled examples ...
Comments