Abstract
Learning from Label Proportions (LLP) is a machine learning problem where the training data are composed of bags of instances, and only the class label proportions for each bag are given. In some domains, we can directly obtain label distributions; for example, one can use census statistics and social media user information grouped by location to build a classifier for user demographics. However, label proportions are unavailable in many domains, such as product review sites. The solution is to modify the model fit on data from where label proportion are available domains (the source domain) to apply to a domain where the label distributions are not available (target domain). Such problems can be regarded as the unsupervised domain adaptation problems in an LLP setting. The goal of this paper is to introduce domain adaptation methods to the original LLP solutions such that the proposed model can classify instances from a new domain. We propose a model combining domain-adversarial neural network (DANN) and label regularization, which can be fit on the source-domain bags and predict labels for target-domain instances. This approach requires only label proportions in the source domain. Our experiments on both synthetic tasks and sentiment classification tasks indicate a noticeable improvement in accuracy as compared to using LLP without domain adaptation.
Similar content being viewed by others
Data availability
No datasets were generated during this study.
References
Ardehaly EM, Culotta A. Inferring latent attributes of twitter users with label regularization. In: Proceedings of the 2015 conference of the north american chapter of the association for computational linguistics: Human language technologies, 2015. p. 185–195.
Ardehaly EM, Culotta A. Domain adaptation for learning from label proportions using self-training. In: IJCAI, 2016. p. 3670–3676.
Ardehaly EM, Culotta A. Co-training for demographic classification using deep learning from label proportions. In: 2017 IEEE International Conference on Data Mining Workshops (ICDMW), IEEE 2017. p. 1017–1024.
Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M. Unsupervised domain adaptation by domain invariant projection. In: Proceedings of the IEEE International Conference on Computer Vision, 2013. p. 769–776.
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW. A theory of learning from different domains. Mach Learn. 2010;79(1):151–75.
Blitzer J, Dredze M, Pereira F. Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In: Proceedings of the 45th annual meeting of the association of computational linguistics, 2007. p. 440–447.
Borgwardt KM, Gretton A, Rasch MJ, Kriegel HP, Schölkopf B, Smola AJ. Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics. 2006;22(14):e49–57.
Bortsova G, Dubost F, Ørting S, Katramados I, Hogeweg L, Thomsen L, Wille M, de Bruijne M. Deep learning from label proportions for emphysema quantification. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11, Springer; 2018. p. 768–776.
Chen T, Yu FX, Chen J, Cui Y, Chen YY, Chang SF. Object-based visual sentiment concept analysis and application. In: Proceedings of the 22nd ACM international conference on Multimedia, 2014; p. 367–376.
Fernando B, Habrard A, Sebban M, Tuytelaars T. Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of the IEEE international conference on computer vision, 2013. p. 2960–2967.
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V. Domain-adversarial training of neural networks. J Mach Learn Res. 2016;17(1):2030–96.
Gong B, Grauman K, Sha F. Connecting the dots with landmarks: Discriminatively learning domain-invariant features for unsupervised domain adaptation. In: International Conference on Machine Learning, PMLR 2013. p. 222–230.
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial networks. 2014. arXiv preprint arXiv:1406.2661.
Gopalan R, Li R, Chellappa R. Domain adaptation for object recognition: An unsupervised approach. In: 2011 international conference on computer vision, IEEE 2011. p. 999–1006.
Hong W, Wang Z, Yang M, Yuan J. Conditional generative adversarial network for structured domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. p. 1335–1344.
Huang J, Gretton A, Borgwardt K, Schölkopf B, Smola A. Correcting sample selection bias by unlabeled data. Adv Neural Inf Process Syst. 2006;19:601–8.
Lai KT, Yu FX, Chen MS, Chang SF. Video event detection by inferring temporal instance labels. In: Proceedings of the ieee conference on computer vision and pattern recognition, 2014. p. 2243–2250.
Liu J, Wang B, Qi Z, Tian Y, Shi Y. Learning from label proportions with generative adversarial networks. 2019. arXiv preprint arXiv:1909.02180
Mann GS, McCallum A. Generalized expectation criteria for semi-supervised learning with weakly labeled data. J Mach Learn Res. 2010;11(2):955–84.
Pan SJ, Tsang IW, Kwok JT, Yang Q. Domain adaptation via transfer component analysis. IEEE Trans Neural Netw. 2010;22(2):199–210.
Patrini G, Nock R, Rivera P, Caetano T. (almost) no label no cry. In: Advances in Neural Information Processing Systems, 2014. p. 190–198.
Quadrianto N, Smola AJ, Caetano TS, Le QV. Estimating labels from label proportions. J Mach Learn Res. 2009;10:2349–74.
Rueping S. Svm classifier estimation from group probabilities. In: ICML 2010.
Shi Y, Liu J, Wang B, Qi Z, Tian Y. Deep learning from label proportions with labeled samples. Neural Netw. 2020;128:73–81.
Sun T, Sheldon D, O’Connor B. A probabilistic approach for learning with label proportions applied to the us presidential election. In: 2017 IEEE International Conference on Data Mining (ICDM), IEEE 2017. p. 445–454.
Tzeng E, Hoffman J, Saenko K, Darrell T. Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017. p. 7167–7176.
Yelp: Yelp dataset 2019. https://www.kaggle.com/yelp-dataset/yelp-dataset/version/9. [Online; Accessed 26 June 2021].
Yu FX, Choromanski K, Kumar S, Jebara T, Chang SF. On learning from label proportions. 2014. arXiv preprint arXiv:1402.5902.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This work was supported by National Science Foundation (1618244), (1927407), (1917112), (2133960).
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, X., Culotta, A. Domain Adaptation for Learning from Label Proportions Using Domain-Adversarial Neural Network. SN COMPUT. SCI. 4, 615 (2023). https://doi.org/10.1007/s42979-023-02090-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-02090-8