Prediction Reweighting for Domain Adaptation

There are plenty of classification methods that perform well when training and testing data are drawn from the same distribution. However, in real applications, this condition may be violated, which causes degradation of classification accuracy. Domain adaptation is an effective approach to address this problem. In this paper, we propose a general domain adaptation framework from the perspective of prediction reweighting, from which a novel approach is derived. Different from the major domain adaptation methods, our idea is to reweight predictions of the training classifier on testing data according to their signed distance to the domain separator, which is a classifier that distinguishes training data (from source domain) and testing data (from target domain). We then propagate the labels of target instances with larger weights to ones with smaller weights by introducing a manifold regularization method. It can be proved that our reweighting scheme effectively brings the source and target domains closer to each other in an appropriate sense, such that classification in target domain becomes easier. The proposed method can be implemented efficiently by a simple two-stage algorithm, and the target classifier has a closed-form solution. The effectiveness of our approach is verified by the experiments on artificial datasets and two standard benchmarks, a visual object recognition task and a cross-domain sentiment analysis of text. Experimental results demonstrate that our method is competitive with the state-of-the-art domain adaptation algorithms.

[1]  Dacheng Tao,et al.  Bregman Divergence-Based Regularization for Transfer Subspace Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[2]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[3]  Krishnakumar Balasubramanian,et al.  Unsupervised Supervised Learning II: Margin-Based Classification without Labels , 2011, AISTATS.

[4]  Hans-Peter Kriegel,et al.  Integrating structured biological data by Kernel Maximum Mean Discrepancy , 2006, ISMB.

[5]  Fuzhen Zhuang,et al.  Multi-task Semi-supervised Semantic Feature Learning for Classification , 2012, 2012 IEEE 12th International Conference on Data Mining.

[6]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[7]  Jian Yang,et al.  Instance Selection and Instance Weighting for Cross-Domain Sentiment Classification via PU Learning , 2013, IJCAI.

[8]  William Stafford Noble,et al.  Support vector machine , 2013 .

[9]  Trevor Darrell,et al.  What you saw is not what you get: Domain adaptation using asymmetric kernel transforms , 2011, CVPR 2011.

[10]  I. Olkin,et al.  Multivariate Chebyshev Inequalities , 1960 .

[11]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[12]  Kristen Grauman,et al.  Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation , 2013, ICML.

[13]  Y. Rinott On normal approximation rates for certain sums of dependent random variables , 1994 .

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  Rui Xia,et al.  A POS-based Ensemble Model for Cross-domain Sentiment Classification , 2011, IJCNLP.

[16]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Hui Xiong,et al.  Mining Distinction and Commonality across Multiple Domains Using Generative Model for Text Classification , 2012, IEEE Transactions on Knowledge and Data Engineering.

[18]  Bernhard Schölkopf,et al.  Correcting Sample Selection Bias by Unlabeled Data , 2006, NIPS.

[19]  Sethuraman Panchanathan,et al.  A Two-Stage Weighting Framework for Multi-Source Domain Adaptation , 2011, NIPS.

[20]  Ivor W. Tsang,et al.  This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 1 Domain Adaptation from Multiple Sources: A Domain- , 2022 .

[21]  Ivor W. Tsang,et al.  Healing Sample Selection Bias by Source Classifier Selection , 2011, 2011 IEEE 11th International Conference on Data Mining.

[22]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[23]  Ivor W. Tsang,et al.  Heterogeneous Domain Adaptation for Multiple Classes , 2014, AISTATS.

[24]  Philip S. Yu,et al.  Transfer Joint Matching for Unsupervised Domain Adaptation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Ivor W. Tsang,et al.  Transfer Ordinal Label Learning , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Ioana Popescu,et al.  Optimal Inequalities in Probability Theory: A Convex Optimization Approach , 2005, SIAM J. Optim..

[27]  Ivan Marsic,et al.  Covariate Shift in Hilbert Space: A Solution via Sorrogate Kernels , 2013, ICML.

[28]  Brian C. Lovell,et al.  Domain Adaptation on the Statistical Manifold , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Michael I. Jordan,et al.  A Robust Minimax Approach to Classification , 2003, J. Mach. Learn. Res..

[30]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[31]  Thomas Kalt,et al.  A New Probabilistic Model of Text Classification and Retrieval , 1998 .

[32]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[33]  Avishek Saha,et al.  Active Supervised Domain Adaptation , 2011, ECML/PKDD.

[34]  Thorsten Joachims,et al.  A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization , 1997, ICML.

[35]  Philip S. Yu,et al.  Adaptation Regularization: A General Framework for Transfer Learning , 2014, IEEE Transactions on Knowledge and Data Engineering.

[36]  Qiang Yang,et al.  Cross-domain sentiment classification via spectral feature alignment , 2010, WWW '10.

[37]  Andrew McCallum,et al.  A comparison of event models for naive bayes text classification , 1998, AAAI 1998.

[38]  Cong Li,et al.  A Unifying Framework for Typical Multitask Multiple Kernel Learning Problems , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[39]  Fuzhen Zhuang,et al.  Effectively Constructing Reliable Data for Cross-Domain Text Classification , 2012, Intelligent Information Processing.

[40]  Trevor Darrell,et al.  Continuous Manifold Based Adaptation for Evolving Visual Domains , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Philip S. Yu,et al.  Partially Supervised Classification of Text Documents , 2002, ICML.

[42]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[43]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[44]  Ivor W. Tsang,et al.  Learning Target Predictive Function without Target Labels , 2012, 2012 IEEE 12th International Conference on Data Mining.

[45]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

[46]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.