Felix Ott
ABSTRACT
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target domain to learn a domain-invariant representation that reduces domain discrepancy. This paper proposes a novel supervised DA based on two steps. First, we search for an optimal class-dependent transformation from the source to the target domain from a few samples. We consider optimal transport methods such as the earth mover's distance, Sinkhorn transport and correlation alignment. Second, we use embedding similarity techniques to select the corresponding transformation at inference. We use correlation metrics and higher-order moment matching techniques. We conduct an extensive evaluation on time-series datasets with domain shift including simulated and various online handwriting datasets to demonstrate the performance.
Supplemental Material
Available for Download
- Jason Altschuler, Jonathan Weed, and Philippe Rigollet. 2017. Near-Linear Time Approximation Algorithms for Optimal Transport via Sinkhorn Iterations. In Advances in Neural Information Processing Systems (NIPS). 1961--1971.Google Scholar
- Mahsa Baktashmotlagh, Mehrtash Harandi, and Mathieu Salzmann. 2016. Distribution-Matching Embedding for Visual Domain Adaptation. In Journal of Machine Learning Research (JMLR), Vol. 17. 1--30.Google Scholar
- Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. 2006. SURF: Speeded Up Robust Features. In Europ. Conf. on Computer Vision (ECCV), Vol. 3951. 404--417. https://doi.org/10.1007/11744023_32Google Scholar
- Shai Ben-David, John Blitzer, Koby Crammer, Alex kulesza, Fernando Pereira, and Jennifer Wortmann Vaughan. 2009. A Theory of Learning from Different Domains. In Machine Learning, Vol. 79. 151--175.Google ScholarDigital Library
- Shai Ben-David, John Blitzer, Koby Crammer, and Fernando Pereira. 2006. Analysis of Representations for Domain Adaptation. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
- John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman. 2007. Learning Bounds for Domain Adaptation. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
- Jian-Feng Cai, Emmanuel J. Candés, and Zuowei Shen. 2008. A Singular Value Thresholding Algorithm for Matrix Completion. In arXiv:0810.3286.Google Scholar
- Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen, Keli Zhang, Junjian Ye, Zhuozhang Li, Xiaoyan Yang, and Zhenjie Zhang. 2014. Time Series Domain Adaptation via Sparse Associative Structure Alignment. In Association for the Advancement of Artificial Intelligence (AAAI), Vol. 216. 76--102.Google Scholar
- James Chapman and Hao-Ting Wang. 2021. CCA-Zoo: A Collection of Regularized, Deep Learning based, Kernel, and Probabilistic CCA Methods in a scikit-learn Style Framework. In Journal of Open Source Software (JOSS), Vol. 6(68).Google ScholarCross Ref
- Chao Chen, Zhihong Chen, Boyuan Jiang, and Xinyu Jin. 2019. Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation. In Association for the Advancement of Artificial Intelligence (AAAI), Vol. 33(1). 3296--3303.Google Scholar
- Chao Chen, Zhihang Fu, Zhihong Chen, Sheng Jin, Zhaowei Cheng, Xinyu Jin, and Xian sheng Hua. 2020. HoMM: Higher-Order Moment Matching for Unsupervised Domain Adaptation. In Association for the Advancement of Artificial Intelligence (AAAI), Vol. 34(4). 3422--3429.Google Scholar
- Long Chen, Hanwang Zhang, Jun Xiao, Wei Liu, and Shih-Fu Chang. 2018. Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, 1043--1052. https://doi.org/10.1109/CVPR.2018.00115Google Scholar
- Anoop Cherian, Suvrit Sra, Arindam Banerjee, and Nikolaos Papanikolopoulos. 2012. Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices. In Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 35(9). 2161--2174.Google ScholarDigital Library
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. In arXiv:1412.3555.Google Scholar
- Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron Courville, and Yoshua Bengio. 2015. A Recurrent Latent Variable Model for Sequential Data. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
- Nicolas Courty, Rémi Flamary, Devis Tuia, and Alain Rakotomamonjy. 2016. Optimal Transport for Domain Adaptation. In Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 39(9). 1853--1865. https://doi.org/10.1109/TPAMI.2016.2615921Google ScholarDigital Library
- Marco Cuturi. 2013. Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
- Marco Cuturi and David Avis. 2014. Ground Metric Learning. In Journal of Machine Learning Research (JMLR), Vol. 15. 533--564.Google ScholarDigital Library
- Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, and Eamonn Keogh. 2018. The UCR Time-Series Archive. In arXiv:1810.07758.Google Scholar
- Oscar Day and Taghi M. Khoshgoftaar. 2017. A Survey on Heterogeneous Transfer Learning. In Journal of Big Data, Vol. 4(29).Google Scholar
- Paulo Roberto de Oliveira da Costa, Alp Akçay, Yingqian Zhang, and Uzay Kaymak. 2020. Remaining Useful Lifetime Prediction via Deep Domain Adaptation. In Reliability Engineering & System Saftey, Vol. 195. https://doi.org/10.1016/j.ress.2019.106682Google Scholar
- Fatemeh Dorri and Ali Ghodsi. 2012. Adapting Component Analysis. In Intl. Conf. on Data Mining. Brussels, Belgium, 846--851. https://doi.org/10.1109/ICDM.2012.85Google Scholar
- Lixin Duan, Ivor W. Tsang, and Dong Xu. 2012. Domain Transfer Multiple Kernel Learning. In Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 34(3). 465--479.Google ScholarDigital Library
- Kilian Fatras, Younes Zine, Szymon Majewski, Rémi Flamary, Rémi Gribonval, and Nicolas Courty. 2021. Minibatch Optimal Transport Distances: Analysis and Applications. In arXiv:2101.01792.Google Scholar
- Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier, Charlotte Pelletier, Daniel F. Schmidt, Jonathan Weberf, Geoffrey I. Webb, Lhassane Idoumghar, Pierre-Alain Muller, and François Petitjean. 2019. InceptionTime: Finding AlexNet for Time-Series Classification. In arXiv:1909.04939.Google Scholar
- Basura Fernando, Amaury Habrard, Marc Sebban, and Tinne Tuytelaars. 2013. Unsupervised Visual Domain Adaptation Using Subspace Alignment. In Intl. Conf. on Computer Vision (ICCV). Sydney, Australia, 2960--2967.Google Scholar
- Sira Ferradans, Nicolas Papadakis, Gabriel Peyré, and Jean-François Aujol. 2013. Regularized Discrete Optimal Transport. In Proc. Scale Space Variational Methods Comput. Vis. 428--439.Google ScholarCross Ref
- Rémi Flamary, Nicolas Courty, Alexandre Gramfort, Mokhtar Z. Alaya, Aurélie Boisbunon, Stanislas Chambon, Laetitia Chapel, Adrien Corenflos, Kilian Fatras, Nemo Fournier, Léo Gautheron, Nathalie T. H. Gayraud, Hicham Janati, Alain Rakotomamonjy, Ievgen Redko, Antoine Rolet, Antony Schutz, Vivien Seguy, Danica J. Sutherland, Romain Tavenard, Alexander Tong, and Titouan Vayer. 2021. POT: Python Optimal Transport. In Journal of Machine Learning Research (JMLR), Vol. 22. 1--8. https://pythonot.github.io/index.htmlGoogle Scholar
- Rémi Flamary, Nicolas Courty, Alain Rakotomamonjy, and Devis Tuia. 2014. Optimal Transport with Laplacian Regularization. In Advances in Neural Information Processing Systems (NIPS) Workshop on Optimal Transport and Machine Learning. Montréal, Canada.Google Scholar
- Muhammad Ghifary, W. Bastiaan Kleijn, and Mengjie Zhang. 2014. Domain Adaptive Neural Networks for Object Recognition. In Pacific Rim Intl. Conf. on Artificial Intelligence (PRICAI). Gold Coast, Australia.Google Scholar
- Boqing Gong, Kristen Grauman, and Fei Sha. 2014. Learning Kernels for Unsupervised Domain Adaptation with Applications to Visual Object Recognition. In Intl. Journal of Computer Vision (IJCV), Vol. 109. 3--27.Google ScholarDigital Library
- Boqing Gong, Yuan Shi, Fei Sha, and Kristen Grauman. 2012. Geodesic Flow Kernel for Unsupervised Domain Adaptation. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Providence, RI, 2066--2073.Google Scholar
- Mehrtash Harandi, Mathieu Salzmann, and Fatih Porikli. 2014. Bregman Divergences for Infinite Dimensional Covariance Matrices. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Columbus, OH.Google Scholar
- Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2019. Bag of Tricks for Image Classification with Convolutional Neural Networks. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, 558--567.Google Scholar
- Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Intl. Conf. on Machine Learning (ICML), Vol. 97. 2790--2799.Google Scholar
- Jeremy Howard and Sebastian Ruder. 2018. Universal Language Model Fine-Tuning for Text Classification. In Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL), Vol. 1. Melbourne, Australia, 328--339.Google ScholarCross Ref
- Hailin Hu, MingJian Tang, and Chengcheng Bai. 2020. DATSING: Data Augmented Time-Series Forecasting with Adversarial Domain Adaptation. In ACM Intl. Conf. on Information & Knowledge Management (CIKM). 2061--2064.Google ScholarDigital Library
- Jiayuan Huang, Alexander J. Smola, Arthur Gretton, Karsten M. Borgwardt, and Bernhard Schölkopf. 2006. Correcting Sample Selection Bias by Unlabeled Data. In Advances in Neural Information Processing Systems (NIPS). 601--608.Google Scholar
- Xin Huang, Yuxin Peng, and Mingkuan Yuan. 2020. MHTN: Modal-Adversarial Hybrid Transfer Network for Cross-Modal Retrieval. In Trans. on Cybernetics, Vol. 50(3). 1047--1059. https://doi.org/10.1109/TCYB.2018.2879846Google ScholarCross Ref
- Hal Daumé III. 2007. Frustratingly Easy Domain Adaptation. In Association of Computational Linguistics (ACL). Prague, Czech Republic, 256--263.Google Scholar
- Junguang Jiang, Ximei Wang, Mingsheng Long, and Jianmin Wang. 2020. Resource Efficient Domain Adaptation. In ACM Intl. Conf. on Multimedia (ACMMM). 2220--2228.Google Scholar
- Min Jiang, Wenzhen Huang, Zhongqiang Huang, and Gary G. Yen. 2015. Integration of Global and Local Metrics for Domain Adaptation Learning via Dimensionality Reduction. In Trans. on Cybernetics, Vol. 47(1). 38--51. https://doi.org/10.1109/TCYB.2015.2502483Google ScholarCross Ref
- Yiaoyong Jin, Youngsuk Park, Danielle C. Maddix, Hao Wang, and Yuyang Wang. 2021. Domain Adaptation for Time Series Forecasting via Attention Sharing. In arXiv:2102.06828.Google Scholar
- L. V. Kantorovitch. 2006. On the Translocation of Masses. In Journal of Mathematical Sciences, Vol. 133. 1381--1382.Google ScholarCross Ref
- Fazle Karim, Somshubra Majumdar, Houshang Darabi, and Shun Chen. 2017. LSTM Fully Convolutional Networks for Time-Series Classification. In arXiv:1709.05206.Google Scholar
- Andreas Klaß, Sven M. Lorenz, Martin W. Lauer-Schmaltz, David Rügamer, Bernd Bischl, Christopher Mutschler, and Felix Ott. 2022. Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift. In arXiv:2206.08640.Google Scholar
- Feng Liu, Guangquan Zhang, and Jie Lu. 2020. Heterogeneous Domain Adaptation: An Unsupervised Approach. In Trans. on Neural Networks and Learning Systems, Vol. 31(12). 5588--5602. https://doi.org/10.1109/TNNLS.2020.2973293Google Scholar
- Mingsheng Long, Yue Cao, Lianmin Wang, and Michael I. Jordan. 2015. Learning Transferable Features with Deep Adaptation Networks. In Intl. Conf. on Machine Learning (ICML), Vol. 37. 97--105.Google Scholar
- Mingsheng Long, Jianmin Wang, Guiguang Ding, Sinno Jialin Pan, and Philip S. Yu. 2014. Adaptation Regularization: A General Framework for Transfer Learning. In Trans. on Knowledge and Data Engineering, Vol. 26(5).Google Scholar
- Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, and Philip S. Yu. 2013. Transfer Feature Learning with Joint Distribution Adaptation. In Intl. Conf. on Computer Vision (ICCV). Sydney, Australia, 2200--2207. https://doi.org/10.1109/ICCV.2013.274Google Scholar
- Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, and Philip S. Yu. 2014. Transfer Joint Matching for Unsupervised Domain Adaptation. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Columbus, OH, 1410--1417. https://doi.org/10.1109/CVPR.2014.183Google Scholar
- Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I. Jordan. 2016. Unsupervised Domain Adaptation with Residual Transfer Networks. In Advances on Neural Information Processing Systems (NIPS). 136--144.Google ScholarDigital Library
- Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I. Jordan. 2017. Deep Transfer Learning with Joint Adaptation Networks. In Intl. Conf. on Machine Learning (ICML), Vol. 70. 2208--2217.Google Scholar
- Yong Luo, Tongliang Liu, Yonggang Wen, and Dacheng Tao. 2018. Online Heterogeneous Transfer Metric Learning. In Intl. Joint Conf. on Artificial Intelligence (IJCAI). 2525--2531.Google Scholar
- Maher Moakher and Philipp G. Batchelor. 2006. Symmetric Positive-Definite Matrices: From Geometry to Applications and Visualization. In Visualization and Processing of Tensor Fields. Mathematics and Visualization, Springer, Berlin, Heidelberg.Google Scholar
- Trung Thanh Nguyen, Tomi Silander, Zhuoru Li, and Tze-Yun Leong. 2017. Scalable Transfer Learning in Heterogeneous, Dynamic Environments. In Artificial Intelligence, Vol. 247. 70--94. https://doi.org/10.1016/j.artint.2015.09.013Google ScholarCross Ref
- Ignacio Oguiza. 2020. tsai - A State-of-the-art Deep Learning Library for Time- Series and Sequential Data. Github. https://github.com/timeseriesAI/tsaiGoogle Scholar
- Felix Ott, David Rügamer, Lucas Heublein, Bernd Bischl, and Christopher Mutschler. 2022. Cross-Modal Common Representation Learning with Triplet Loss Functions. In arXiv:2202.07901.Google Scholar
- Felix Ott, David Rügamer, Lucas Heublein, Bernd Bischl, and Christopher Mutschler. 2022. Joint Classification and Trajectory Regression of Online Handwriting using a Multi-Task Learning Approach. In Proc. of the IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV). Waikoloa, HI, 266--276.Google ScholarCross Ref
- Felix Ott, David Rügamer, Lucas Heublein, Tim Hamann, Jens Barth, Bernd Bischl, and Christopher Mutschler. 2022. Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens. In arXiv:2202.07036.Google Scholar
- Felix Ott, Mohamad Wehbi, Tim Hamann, Jens Barth, Björn Eskofier, and Christopher Mutschler. 2020. The OnHW Dataset: Online Handwriting Recognition from IMU-Enhanced Ballpoint Pens with Machine Learning. In Proc. of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Vol. 4(3), Article 92. Cancún, Mexico. https://doi.org/10.1145/3411842Google ScholarDigital Library
- Sinno Jialin Pan, Ivor W. Tsang, James T. Kwok, and Qiang Yang. 2011. Domain Adaptation via Transfer Component Analysis. In Trans. on Neural Networks, Vol. 22(2). 199--210. https://doi.org/10.1109/TNN.2010.2091281Google ScholarDigital Library
- Sinno Jialin Pan and Qiang Yang. 2009. A Survey on Transfer Learning. In Trans. on Knowledge and Data Engineering, Vol. 22(10). 1345--1359. https://doi.org/10.1109/TKDE.2009.191Google ScholarDigital Library
- Vishal M. Patel, Raghuraman Gopalan, Ruonan Li, and Rama Chellappa. 2015. Visual Domain Adaptation: A Survey of Recent Advances. In IEEE Signal Processing Magazine, Vol. 32(3). 53--69. https://doi.org/10.1109/MSP.2014.2347059Google ScholarCross Ref
- Karl Pearson. 1920. Notes on the History of Correlation. In Biometrika, Vol. 13(1). 25--45.Google ScholarCross Ref
- Réjean Plamondon and Sargur N. Srihari. 2000. Online and Off-line Handwriting Recognition: A Comprehensive Survey. In Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 22(1). 63--84.Google ScholarDigital Library
- Sanjay Purushotham, Wilka Carvalho, Tanachat Nilanon, and Yan Liu. 2017. Variational Recurrent Adversarial Deep Domain Adaptation. In Intl. Conf. on Learning Representations (ICLR).Google Scholar
- Elahe Rahimian, Soheil Zabihi, Seyed Farokh Atashzar, Amir Asif, and Arash Mohammadi. 2019. XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification. In arXiv:1911.03803.Google Scholar
- Viresh Ranjan, Nikhil Rasiwasia, and C. V. Jawahar. 2015. Multi-Label Cross-Modal Retrieval. In Intl. Conf. on Computer Vision (ICCV). Santiage de Chile, Chile, 4094--4102. https://doi.org/10.1109/ICCV.2015.466Google Scholar
- Esmat Rashedi, Hossein Nezamabadi-pour, and Saeid Saryazdi. 2013. A Simultaneous Feature Adaptation and Feature Selection Method for Content-based Image Retrieval Systems. In Knowledge-Based Systems, Vol. 39. 85--94.Google ScholarDigital Library
- Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. 2010. Adapting Visual Category Models to New Domains. In Europ. Conf. on Computer Vision (ECCV), Vol. 6314. 213--226.Google ScholarCross Ref
- Filippo Santambrogio. 2015. Optimal Transport for Applied Mathematicians - Calculus of Variations, PDEs, and Modeling. In Progress in Nonlinear Differential Equations and Their Applications (PNLDE), Vol. 87.Google Scholar
- Sandeepkumar Satpal and Sunita Sarawagi. 2007. Domain Adaptation of Conditional Probability Models Via Feature Subsetting. In Europ. Conf. on Principles of Data Mining and Knowledge Discovery (ECPDMKD), Vol. 4702. 224--235.Google Scholar
- Ling Shao, Fan Zhu, and Xuelong Li. 2014. Transfer Learning for Visual Categorization: A Survey. In Trans. on Neural Networks and Learning Systems, Vol. 26(5). 1019--1034. https://doi.org/10.1109/TNNLS.2014.2330900Google ScholarCross Ref
- Baochen Sun, Jiashin Feng, and Kate Saenko. 2016. Correlation Alignment for Unsupervised Domain Adaptation. In arXiv:1612.01939.Google Scholar
- Baochen Sun and Kate Saenko. 2015. Subspace Distribution Alignment for Unsupervised Domain Adaptation. In British Machine Vision Conf. (BMVC), Vol. 24. 10. https://doi.org/10.5244/C.29.24Google Scholar
- Baochen Sun and Kate Saenko. 2016. Deep CORAL: Correlation Alignment for Deep Domain Adaptation. In Europ. Conf. on Computer Vision (ECCV), Vol. 9915. 443--450.Google Scholar
- Chang Wei Tan, Angus Dempster, Christoph Bergmeir, and Geoffrey I. Webb. 2021. MultiRocket: Multiple Pooling Operators and Transformations for Fast and Effective Time-Series Classification. In arXiv:2102.00457.Google Scholar
- Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Jing Jiang, and Michael Blumenstein. 2020. Rethinking 1D-CNN for Time-Series Classification: A Stronger Baseline. In arXiv:2002.10061.Google Scholar
- Benjamin Tardy, Jordi Inglada, and Julien Michel. 2019. Assessment of Optimal Transport for Operational Land-Cover Mapping Using High-Resolution Satellite Images Time Series Without Reference Data of the Mapping Period. In MDPI Remote Sensing, Vol. 11(9). https://doi.org/10.3390/rs11091047Google ScholarCross Ref
- Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. 2014. Deep Domain Confusion: Maximizing for Domain Invariance. In arXiv:1412.3474.Google Scholar
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. In Journal of Machine Learning Research (JMLR), Vol. 9(86). 2579--2605.Google Scholar
- Cédric Villani. 2008. Optimal Transport, Old and New. In Springer.Google Scholar
- Chang Wang and Sridhar Mahadevan. 2019. Manifold Alignment using Procrustes Analysis. In MDPI Remote Sensing, Vol. 11(9). https://doi.org/10.1145/1390156.1390297Google Scholar
- Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, and Philip S. Yu. 2017. Stratified Transfer Learning for Cross-Domain Activity Recognition. In arXiv:1801.00820.Google Scholar
- Zhiguang Wang, Weizhong Yan, and Tim Oates. 2016. Time-Series Classification from Scratch with Deep Neural Networks: A Strong Baseline. In arXiv:1611.06455.Google Scholar
- Garrett Wilson, Janardhan Rao Doppa, and Diane J. Cook. 2020. Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data. In ACM Intl. Conf. on Knowledge Discovery & Data Mining (SIGKDD). 1768--1778.Google Scholar
- Yuguang Yan, Qingyao Wu, Mingkui Tan, Michael K. Ng, Huaqing Min, and Ivor W. Tsang. 2017. Online Heterogeneous Transfer by Hedge Ensemble of Offline and Online Decisions. In Trans. on Neural Networks and Learning Systems, Vol. 29(7). 3252--3263.Google Scholar
- Liu Yang, Liping Jing, Jian Yu, and Michael K. Ng. 2015. Learning Transferred Weights From Co-Occurrence Data for Heterogeneous Transfer Learning. In Trans. on Neural Networks and Learning Systems, Vol. 27(11). 2187--2200. https://doi.org/10.1109/TNNLS.2017.2751102Google ScholarCross Ref
- George Zerveas, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty, and Carsten Eickhoff. 2021. A Transformer-based Framework for Multivariate Time-Series Representation Learning. In ACM Intl. Conf. on Knowledge Discovery & Data Mining (SIGKDD). 2114--2124.Google ScholarDigital Library
- Youshan Zhang. 2021. A Survey of Unsupervised Domain Adaptation for Visual Recognition. In arXiv:2112.06745.Google Scholar
- Zhen Zhang, Mianzhi Wang, Yan Huang, and Arye Nehorai. 2018. Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation. In Intl. Conf. on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, 3437--3445. https://doi.org/10.1109/CVPR.2018.00362Google Scholar
- Peilin Zhao, Steven C. H. Hoi, Jialei Wang, and Bin Li. 2014. Online Transfer Learning. In Research Collection School of Information Systems, Vol. 216. 76--102.Google Scholar
- Fuzhen Zhuang, Xiaohu Cheng, Ping Luo, Sinno Jialin Pan, and Qing He. 2018. Supervised Representation Learning with Double Encoding-Layer Autoencoder for Transfer Learning. In ACM Trans. on Intelligent Systems and Technology (TIST), Vol. 9(2), Article 16. 1--17.Google Scholar
- Hankz Hankui Zhuo and Qiang Yang. 2014. Action-Model Acquisition for Planning via Transfer Learning. In Artificial Intelligence, Vol. 212. 80--103. https://doi.org/10.1016/j.artint.2014.03.004Google ScholarDigital Library
- Xiawou Zou, Zidong Wang, Qi Li, and Weiguo Sheng. 2019. Integration of Residual Network and Convolutional Neural Network Along with Various Activation Functions and Global Pooling for Time-Series Classification. In Neurocomputing, Vol. 367. 39--45.Google ScholarDigital Library
Recommendations
Variate Associated Domain Adaptation for Unsupervised Multivariate Time Series Anomaly Detection
Multivariate Time Series Anomaly Detection (MTS-AD) is crucial for the effective management and maintenance of devices in complex systems such as server clusters, spacecrafts and financial systems etc. However, upgrade or cross-platform deployment of ...
Unsupervised sub-domain adaptation using optimal transport
AbstractWe focus on domain adaptation, a branch of transfer learning that concentrates on transferring knowledge from one domain to another when the data distributions differ. Specifically, we investigate unsupervised domain adaptation methods, which ...
Highlights- Unsupervised sub-domain adaptation extracts pertinent features for every domain category.
- Our proposed OTSA model for unsupervised domain adaptation shows great promise.
- We introduce LMMD and SWD loss to reduce distribution ...
Zero-Shot Deep Domain Adaptation
Computer Vision – ECCV 2018AbstractDomain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during training. ...
Comments