{"type":"ScholarlyArticle","title":"R-SVM+: Robust Learning with Privileged Information","authors":[{"name":"Xue Li","slug":"xue-li","given":"Xue","family":"Li","affiliation":"School of Computer Science , Wuhan University , China; LIESMARS , Wuhan University , China"},{"name":"Bo Du","slug":"bo-du","given":"Bo","family":"Du","affiliation":"School of Computer Science , Wuhan University , China"},{"name":"Chang Xu","slug":"chang-xu","given":"Chang","family":"Xu","affiliation":"UBTECH Sydney AI Centre , SIT , FEIT , University of Sydney , Australia"},{"name":"Yipeng Zhang","slug":"yipeng-zhang","given":"Yipeng","family":"Zhang","affiliation":"School of Computer Science , Wuhan University , China"},{"name":"Lefei Zhang","slug":"lefei-zhang","given":"Lefei","family":"Zhang","affiliation":"School of Computer Science , Wuhan University , China"},{"name":"Dacheng Tao","slug":"dacheng-tao","given":"Dacheng","family":"Tao","affiliation":"UBTECH Sydney AI Centre , SIT , FEIT , University of Sydney , Australia"}],"abstract":"In practice, the circumstance that training and test data are clean is\r\nnot always satisfied. The performance of existing methods in the learning using\r\nprivileged information (LUPI) paradigm may be seriously challenged, due to the\r\nlack of clear strategies to address potential noises in the data. This paper\r\nproposes a novel Robust SVM+ (RSVM+) algorithm based on a rigorous theoretical analysis.\r\nUnder the SVM+ framework in the LUPI paradigm, we study the lower bound of\r\nperturbations of both example feature data and privileged feature data, which\r\nwill mislead the model to make wrong decisions. By maximizing the lower bound, tolerance\r\nof the learned model over perturbations will be increased. Accordingly, a novel\r\nregularization function is introduced to upgrade a variant form of SVM+. The\r\nobjective function of RSVM+ is transformed into a quadratic programming\r\nproblem, which can be efficiently optimized using off-the-shelf solvers.\r\nExperiments on real-world datasets demonstrate the necessity of studying robust\r\nSVM+ and the effectiveness of the proposed algorithm.","doi":"10.24963/ijcai.2018/334","url":"https://ijcai.org/proceedings/2018/334","pdf":"https://ijcai.org/proceedings/2018/0334.pdf","markdown":"https://ijcai.org/proceedings/2018/334.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/334","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":334,"pages":{"first":2411,"last":2417},"keywords":["Machine Learning: Machine Learning","Machine Learning: Classification"],"videos":[],"references":[{"position":1,"raw":"[Anguita et al., 2013] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J L Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. In 21th European Symposium on Artificial Neural Networks, Com- putational Intelligence and Machine Learning, 2013.","title":"A public domain dataset for human activity recognition using smartphones","authors":"D Anguita, A Ghio, L Oneto, X Parra, J L Reyes-Ortiz","year":"2013","venue":"21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Coleman and Li, 1996] Thomas F. Coleman and Yuying Li. A reflective newton method for minimizing a quadratic function subject to bounds on some of the variables. SIAM Journal on Optimization, 6(4):1040-1058, 1996.","title":"A reflective newton method for minimizing a quadratic function subject to bounds on some of the variables","authors":"Thomas F Coleman, Yuying Li","year":"1996","venue":"SIAM Journal on Optimization","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Feyereisl et al., 2014] Jan Feyereisl, Suha Kwak, Jeany Son, and Bohyung Han. Object localization based on structural SVM using privileged information. In Advances in Neural Information Processing Systems, pages 208- 216, 2014.","title":"Object localization based on structural SVM using privileged information","authors":"Feyereisl","year":"2014","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gould and Toint, 2004] Nick Gould and Philippe L. Toint. Preprocessing for quadratic programming. Springer- Verlag New York, Inc., 2004.","title":"Preprocessing for quadratic programming","authors":"Nick Gould, Philippe L Toint","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hg et al., 2012] R. I. Hg, P. Jasek, C. Rofidal, K. Nasrollahi, T. B. Moeslund, and G. Tranchet. An rgb-d database us- ing microsoft's kinect for windows for face detection. In Eighth International Conference on Signal Image Technol- ogy and Internet Based Systems, pages 42-46, 2012.","title":"An rgb-d database using microsoft's kinect for windows for face detection","authors":"R I Hg, P Jasek, C Rofidal, K Nasrollahi, T B Moeslund, G Tranchet","year":"2012","venue":"Eighth International Conference on Signal Image Technology and Internet Based Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ji et al., 2012] You Ji, Shiliang Sun, and Yue Lu. Multi- task multiclass privileged information support vector ma- chines. In 2012 21st International Conference on Pattern Recognition, pages 2323-2326. IEEE, 2012.","title":"Multitask multiclass privileged information support vector machines","authors":"Ji","year":"2012","venue":"21st International Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[LeCun et al., 1998] Y. L. LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. proc ieee. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Y L Lecun, Leon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"proc ieee. Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2016] Wen Li, Dengxin Dai, Mingkui Tan, Dong Xu, and Luc Van Gool. Fast algorithms for linear and ker- nel SVM+. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2258- 2266, 2016.","title":"Fast algorithms for linear and kernel SVM+","authors":"Wen Li, Dengxin Dai, Mingkui Tan, Dong Xu, Luc Van Gool","year":"2016","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Motiian et al., 2016] Saeid Motiian, Marco Piccirilli, Don- ald A. Adjeroh, and Gianfranco Doretto. Information bot- tleneck learning using privileged information for visual recognition. In Computer Vision and Pattern Recognition, pages 1496-1505, 2016.","title":"Information bottleneck learning using privileged information for visual recognition","authors":"Saeid Motiian, Marco Piccirilli, Donald A Adjeroh, Gianfranco Doretto","year":"2016","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Niu et al., 2012] Lingfeng Niu, Yong Shi, and Jianmin Wu. Learning using privileged information with L-1 support vector machine. In IEEE/WIC/ACM International Con- ferences on Web Intelligence and Intelligent Agent Tech- nology, volume 3, pages 10-14, 2012.","title":"Learning using privileged information with L-1 support vector machine","authors":"Lingfeng Niu, Yong Shi, Jianmin Wu","year":"2012","venue":"IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Pechyony and Vapnik, 2010] Dmitry Pechyony and Vladimir Vapnik. On the theory of learning with privi- leged information. In International Conference on Neural Information Processing Systems, pages 1894-1902, 2010.","title":"On the theory of learning with privileged information","authors":"Dmitry Pechyony, Vladimir Vapnik","year":"2010","venue":"International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sharmanska et al., 2013] Viktoriia Sharmanska, Novi Quadrianto, and Christoph H Lampert. Learning to rank using privileged information. In Proceedings of the IEEE International Conference on Computer Vision, pages 825-832, 2013.","title":"Viktoriia Sharmanska, Novi Quadrianto, and Christoph H Lampert. Learning to rank using privileged information","authors":"Sharmanska","year":"2013","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shen et al., 2014] Jianbing Shen, Yunfan Du, Wenguan Wang, and Xuelong Li. Lazy random walks for superpixel segmentation. IEEE Transactions on Image Processing, 23(4):1451-1462, 2014.","title":"Lazy random walks for superpixel segmentation","authors":"Shen","year":"2014","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Vapnik and Izmailov, 2015] Vladimir Vapnik and Rauf Iz- mailov. Learning using privileged information: similar- ity control and knowledge transfer. Journal of Machine Learning Research, 16(55):2023-2049, 2015.","title":"Vladimir Vapnik and Rauf Izmailov. Learning using privileged information: similarity control and knowledge transfer","authors":"Izmailov Vapnik","year":"2015","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Vapnik and Vashist, 2009] Vladimir Vapnik and Akshay Vashist. A new learning paradigm: Learning using priv- ileged information. Neural Networks, 22(5):544-557, 2009.","title":"Vladimir Vapnik and Akshay Vashist. A new learning paradigm: Learning using privileged information","authors":"Vashist Vapnik","year":"2009","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2018] Wenguan Wang, Jianbing Shen, and Ling Shao. Video salient object detection via fully con- volutional networks. IEEE Transactions on Image Pro- cessing, 27(1):38-49, 2018.","title":"Video salient object detection via fully convolutional networks","authors":"Wang","year":"2018","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2016] Guibiao Xu, Zheng Cao, Bao Gang Hu, and Jose C. Principe. Robust support vector machines based on the rescaled hinge loss function. Pattern Recognition, 63:139-148, 2016.","title":"Robust support vector machines based on the rescaled hinge loss function","authors":"Guibiao Xu, Zheng Cao, Bao Gang Hu, Jose C Principe","year":"2016","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Yang et al., 2017] Xun Yang, Meng Wang, and Dacheng Tao. Person re-identification with metric learning using privileged information. IEEE Transactions on Image Pro- cessing, 27(2):791-805, 2017.","title":"Person re-identification with metric learning using privileged information","authors":"Xun Yang, Meng Wang, Dacheng Tao","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[You et al., 2017] Shan You, Chang Xu, Yunhe Wang, Chao Xu, and Dacheng Tao. Privileged multi-label learning. In Proceedings of the Twenty-Sixth International Joint Con- ference on Artificial Intelligence, IJCAI-17, pages 3336- 3342, 2017.","title":"Privileged multi-label learning","authors":"Shan You, Chang Xu, Yunhe Wang, Chao Xu, Dacheng Tao","year":"2017","venue":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17","doi":null,"url":null,"internal_url":"/proceedings/2017/466"},{"position":20,"raw":"[Zhou et al., 2016] Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan, Ivor W Tsang, Zheng Qin, and Rick Siow Mong Goh. Transfer hashing with privileged information. In Proceedings of the Twenty-Fifth Interna- tional Joint Conference on Artificial Intelligence, pages 2414-2420, 2016.","title":"Transfer hashing with privileged information","authors":"Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan, Ivor W Tsang, Zheng Qin, Rick Siow, Mong Goh","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/344"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}