{"type":"ScholarlyArticle","title":"Distance Metric Facilitated Transportation between Heterogeneous Domains","authors":[{"name":"Han-Jia Ye","slug":"han-jia-ye","given":"Han-Jia","family":"Ye","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Xiang-Rong Sheng","slug":"xiang-rong-sheng","given":"Xiang-Rong","family":"Sheng","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"De-Chuan Zhan","slug":"de-chuan-zhan","given":"De-Chuan","family":"Zhan","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Peng He","slug":"peng-he","given":"Peng","family":"He","affiliation":"Tencent , China"}],"abstract":"Lacking training examples is one of the main obstacles to learning systems. Transfer learning aims to extract and utilize useful information from related datasets and assists the current task effectively. Most existing methods restrict tasks connection on the same feature sets, or require aligned examples cross domains, even cannot take full advantage of the limited label information. In this paper, we focus on transferring between heterogeneous domains, i.e., those with different feature spaces, and propose the Metric Transporation on HEterogeneous REpresentations (MapHere) approach. In particular, an asymmetric transformation map is first learned to compensate the  cross-domain feature difference based on linkage relationship between objects; then the inner-domain discrepancy is further reduced with learned optimal transportation. Note that both source domain and cross-domain relationship are fully utilized in MapHere, which helps improve target classification task a lot.  Experiments on synthetic dataset validate the importance of the ''metric facilitated'' consideration, while results on real-world image and text classification also show the superiority of the proposed MapHere approach.","doi":"10.24963/ijcai.2018/418","url":"https://ijcai.org/proceedings/2018/418","pdf":"https://ijcai.org/proceedings/2018/0418.pdf","markdown":"https://ijcai.org/proceedings/2018/418.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/418","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":418,"pages":{"first":3012,"last":3018},"keywords":["Machine Learning: Multi-instance;Multi-label;Multi-view learning","Machine Learning: Transfer, Adaptation, Multi-task Learning"],"videos":[],"references":[{"position":1,"raw":"[Aljundi et al., 2015] R. Aljundi, R. Emonet, D. Muselet, and M. Sebban. Landmarks-based kernelized subspace alignment for unsupervised domain adaptation. In The 28th IEEE Confer- ence on Computer Vision and Pattern Recognition, pages 56-63, Boston, MA., 2015.","title":"Landmarks-based kernelized subspace alignment for unsupervised domain adaptation","authors":"R Aljundi, R Emonet, D Muselet, M Sebban","year":"2015","venue":"The 28th IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bellet et al., 2015] A. Bellet, A. Habrard, and M. Sebban. Metric learning. Synthesis Lectures on Artificial Intelligence and Ma- chine Learning, 9(1):1-151, 2015.","title":"Metric learning","authors":"A Bellet, A Habrard, M Sebban","year":"2015","venue":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ben-David and Urner, 2012] S. Ben-David and R. Urner. On the hardness of domain adaptation and the utility of unlabeled target samples. In Algorithmic Learning Theory -23rd International Conference, pages 139-153, Lyon, France, 2012.","title":"On the hardness of domain adaptation and the utility of unlabeled target samples","authors":"S Ben-David, R Urner","year":"2012","venue":"Algorithmic Learning Theory -23rd International Conference","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ben-David et al., 2010] S. Ben-David, T. Lu, T. Luu, and D. Pál. Impossibility theorems for domain adaptation. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pages 129-136, Sardinia, Italy, 2010.","title":"Impossibility theorems for domain adaptation","authors":"S Ben-David, T Lu, T Luu, D Pál","year":"2010","venue":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Courty et al., 2017a] N. Courty, R. Flamary, A. Habrard, and A. Rakotomamonjy. Joint distribution optimal transportation for domain adaptation. In Advances in Neural Information Process- ing Systems 30, pages 3733-3742. Cambridge, MA.: MIT Press, 2017.","title":"Joint distribution optimal transportation for domain adaptation","authors":"Courty","year":"2017","venue":"Advances in Neural Information Processing Systems 30","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Courty et al., 2017b] N. Courty, R. Flamary, D. Tuia, and A. Rako- tomamonjy. Optimal transport for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(9):1853-1865, 2017.","title":"Optimal transport for domain adaptation","authors":"Courty","year":"2017","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cuturi, 2013] M. Cuturi. Sinkhorn distances: Lightspeed com- putation of optimal transport. In Advances in Neural Informa- tion Processing Systems 26, pages 2292-2300. Cambridge, MA.: MIT Press, 2013.","title":"Sinkhorn distances: Lightspeed computation of optimal transport","authors":"M Cuturi","year":"2013","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Davis et al., 2007] J. V. Davis, B. Kulis, P. Jain, S. Sra, and I. S. Dhillon. Information-theoretic metric learning. In Proceedings of the 24th International Conference on Machine Learning, pages 209-216, Corvalis, OR., 2007.","title":"Information-theoretic metric learning","authors":"J V Davis, B Kulis, P Jain, S Sra, I S Dhillon","year":"2007","venue":"Proceedings of the 24th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Frogner et al., 2015] C. Frogner, C. Zhang, H. Mobahi, M. Araya- Polo, and T. A. Poggio. Learning with a wasserstein loss. In Advances in Neural Information Processing Systems 28, pages 2053-2061. Cambridge, MA.: MIT Press, 2015.","title":"Learning with a wasserstein loss","authors":"C Frogner, C Zhang, H Mobahi, M Araya-Polo, T A Poggio","year":"2015","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Geng et al., 2011] B. Geng, D. Tao, and C. Xu. DAML: domain adaptation metric learning. IEEE Transactions on Image Pro- cessing, 20(10):2980-2989, 2011.","title":"DAML: domain adaptation metric learning","authors":"B Geng, D Tao, C Xu","year":"2011","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gong et al., 2012] B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2066-2073, Providence, RI., 2012.","title":"Geodesic flow kernel for unsupervised domain adaptation","authors":"B Gong, Y Shi, F Sha, K Grauman","year":"2012","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gretton et al., 2012] A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. J. Smola. A kernel two-sample test. Journal of Machine Learning Research, 13:723-773, 2012.","title":"A kernel two-sample test","authors":"A Gretton, K M Borgwardt, M J Rasch, B Schölkopf, A J Smola","year":"2012","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hoffman et al., 2013] J. Hoffman, E. Rodner, J. Donahue, K. Saenko, and T. Darrell. Efficient learning of domain-invariant image representations. CoRR, abs/1301.3224, 2013.","title":"Efficient learning of domain-invariant image representations","authors":"J Hoffman, E Rodner, J Donahue, K Saenko, T Darrell","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Jaggi, 2013] M. Jaggi. Revisiting frank-wolfe: Projection-free sparse convex optimization. In Proceedings of the 30th Inter- national Conference on Machine Learning, pages 427-435, At- lanta, GA., 2013.","title":"Revisiting frank-wolfe: Projection-free sparse convex optimization","authors":"M Jaggi","year":"2013","venue":"Proceedings of the 30th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jiang and Li, 2017] Q.-Y. Jiang and W.-J. Li. Deep cross-modal hashing. In 2017 IEEE Conference on Computer Vision and Pat- tern Recognition, pages 3270-3278, Honolulu, HI., 2017.","title":"Deep cross-modal hashing","authors":"Q.-Y Jiang, W.-J Li","year":"2017","venue":"2017 IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kolouri et al., 2017] S. Kolouri, S. Rim Park, M. Thorpe, D. Slepcev, and G. K. Rohde. Optimal mass transport: Signal processing and machine-learning applications. IEEE Signal Pro- cessing Magazine, 34(4):43-59, 2017.","title":"Optimal mass transport: Signal processing and machine-learning applications","authors":"S Kolouri, S Park, M Thorpe, D Slepcev, G K Rohde","year":"2017","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kulis et al., 2011] B. Kulis, K. Saenko, and T. Darrell. What you saw is not what you get: Domain adaptation using asymmet- ric kernel transforms. In The 24th IEEE Conference on Com- puter Vision and Pattern Recognition, pages 1785-1792, Col- orado Springs, CO., 2011.","title":"What you saw is not what you get: Domain adaptation using asymmetric kernel transforms","authors":"B Kulis, K Saenko, T Darrell","year":"2011","venue":"The 24th IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li and Zhou, 2015] Y.-F. Li and Z.-H. Zhou. Towards making un- labeled data never hurt. IEEE Transactions on Pattern Analysis and Machine Intelligence., 37(1):175-188, 2015.","title":"Towards making unlabeled data never hurt","authors":"Y.-F Li, Z.-H Zhou","year":"2015","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2014] W. Li, L. Duan, D. Xu, and I. W. Tsang. Learn- ing with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(6):1134-1148, 2014.","title":"Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation","authors":"W Li, L Duan, D Xu, I W Tsang","year":"2014","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Long et al., 2014] M. Long, J. Wang, G. Ding, D. Shen, and Q. Yang. Transfer learning with graph co-regularization. IEEE Transactions on Knowledge and Data Engineering, 26(7):1805- 1818, 2014.","title":"Transfer learning with graph co-regularization","authors":"M Long, J Wang, G Ding, D Shen, Q Yang","year":"2014","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Luo et al., 2016] Y. Luo, Y. Wen, and D. Tao. On combining side information and unlabeled data for heterogeneous multi- task metric learning. In Proceedings of the Twenty-Fifth Inter- national Joint Conference on Artificial Intelligence, pages 1809- 1815, New York, NY., 2016.","title":"On combining side information and unlabeled data for heterogeneous multitask metric learning","authors":"Y Luo, Y Wen, D Tao","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mohri et al., 2012] M. Mohri, A. Rostamizadeh, and A. Talwalkar. Foundations of machine learning. MIT press, 2012.","title":"Foundations of machine learning","authors":"M Mohri, A Rostamizadeh, A Talwalkar","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pan and Yang, 2010] S. J. Pan and Q. Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineer- ing, 22(10):1345-1359, 2010.","title":"A survey on transfer learning","authors":"S J Pan, Q Yang","year":"2010","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Perrot and Habrard, 2015] M. Perrot and A. Habrard. A theoretical analysis of metric hypothesis transfer learning. In Proceedings of the 32nd International Conference on Machine Learning, pages 1708-1717, Lille, France, 2015.","title":"A theoretical analysis of metric hypothesis transfer learning","authors":"M Perrot, A Habrard","year":"2015","venue":"Proceedings of the 32nd International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Perrot et al., 2016] M. Perrot, N. Courty, R. Flamary, and A. Habrard. Mapping estimation for discrete optimal transport. In Advances in Neural Information Processing Systems 29, pages 4197-4205. Cambridge, MA.: MIT Press, 2016.","title":"Mapping estimation for discrete optimal transport","authors":"M Perrot, N Courty, R Flamary, A Habrard","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Shi and Knoblock, 2017] Y. Shi and C. A. Knoblock. Learning with previously unseen features. In Proceedings of the 26th Inter- national Joint Conference on Artificial Intelligence, pages 2722- 2729, Melbourne, Australia, 2017.","title":"Learning with previously unseen features","authors":"Y Shi, C A Knoblock","year":"2017","venue":"Proceedings of the 26th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/379"},{"position":27,"raw":"[Si et al., 2010] S. Si, D. Tao, and B. Geng. Bregman divergence- based regularization for transfer subspace learning. IEEE Trans- action on Knowledge and Data Engineering, 22(7):929-942, 2010.","title":"Bregman divergencebased regularization for transfer subspace learning","authors":"S Si, D Tao, B Geng","year":"2010","venue":"IEEE Transaction on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tommasi et al., 2014] T. Tommasi, F. Orabona, and B. Caputo. Learning categories from few examples with multi model knowl- edge transfer. IEEE Transaction on Pattern Analysis and Ma- chine Intelligence, 36(5):928-941, 2014.","title":"Learning categories from few examples with multi model knowledge transfer","authors":"T Tommasi, F Orabona, B Caputo","year":"2014","venue":"IEEE Transaction on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2014] H. Wang, W. Wang, C. Zhang, and F. Xu. Cross-domain metric learning based on information theory. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pages 2099-2105, Québec, Canada, 2014.","title":"Cross-domain metric learning based on information theory","authors":"H Wang, W Wang, C Zhang, F Xu","year":"2014","venue":"Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Weinberger and Saul, 2009] K. Q. Weinberger and L. K. Saul. Dis- tance metric learning for large margin nearest neighbor classifica- tion. Journal of Machine Learning Research, 10:207-244, 2009.","title":"Distance metric learning for large margin nearest neighbor classification","authors":"K Q Weinberger, L K Saul","year":"2009","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}