{"type":"ScholarlyArticle","title":"E²GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation","authors":[{"name":"Yonghong Luo","slug":"yonghong-luo","given":"Yonghong","family":"Luo","affiliation":"College of Computer Science , Nankai University , Tianjin , China"},{"name":"Ying Zhang","slug":"ying-zhang","given":"Ying","family":"Zhang","affiliation":"College of Computer Science , Nankai University , Tianjin , China"},{"name":"Xiangrui Cai","slug":"xiangrui-cai","given":"Xiangrui","family":"Cai","affiliation":"College of Cyber Science , Nankai Univeristy , Tianjin , China"},{"name":"Xiaojie Yuan","slug":"xiaojie-yuan","given":"Xiaojie","family":"Yuan","affiliation":"College of Computer Science , Nankai University , Tianjin , China; College of Cyber Science , Nankai Univeristy , Tianjin , China"}],"abstract":"The missing values, appear in most of multivariate time series, prevent advanced analysis of multivariate time series data. Existing imputation approaches try to deal with missing values by deletion, statistical imputation, machine learning based imputation and generative imputation. However, these methods are either incapable of dealing with temporal information or multi-stage. This paper proposes an end-to-end generative model E²GAN to impute missing values in multivariate time series. With the help of the discriminative loss and the squared error loss, E²GAN can impute the incomplete time series by the nearest generated complete time series at one stage. Experiments on multiple real-world datasets show that our model outperforms the baselines on the imputation accuracy and achieves state-of-the-art classification/regression results on the downstream applications. Additionally, our method also gains better time efficiency than multi-stage method on the training of neural networks.","doi":"10.24963/ijcai.2019/429","url":"https://ijcai.org/proceedings/2019/429","pdf":"https://ijcai.org/proceedings/2019/0429.pdf","markdown":"https://ijcai.org/proceedings/2019/429.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/429","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":429,"pages":{"first":3094,"last":3100},"keywords":["Machine Learning: Deep Learning","Machine Learning: Time-series;Data Streams","Machine Learning: Learning Generative Models"],"videos":[],"references":[{"position":1,"raw":"[Acar et al., 2010] Evrim Acar, Daniel M Dunlavy, Tamara G Kolda, and Morten Mørup. Scalable ten- sor factorizations with missing data. In Proceedings of the 2010 SIAM international conference on data mining, pages 701-712. SIAM, 2010.","title":"Scalable tensor factorizations with missing data","authors":"Evrim Acar, Tamara G Daniel M Dunlavy, Morten Kolda, Mørup","year":"2010","venue":"Proceedings of the 2010 SIAM international conference on data mining","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Amiri and Jensen, 2016] Mehran Amiri and Richard Jensen. Missing data imputation using fuzzy-rough methods. Neurocomputing, 205:152-164, 2016.","title":"Missing data imputation using fuzzy-rough methods","authors":"Mehran Amiri, Richard Jensen","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Arjovsky et al., 2017] Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial net- works. In ICML, pages 214-223, 2017.","title":"Wasserstein generative adversarial networks","authors":"Arjovsky","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Berglund et al., 2015] Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, and Juha T Karhunen. Bidirectional recurrent neural networks as gen- erative models. In Advances in Neural Information Pro- cessing Systems, pages 856-864, 2015.","title":"Bidirectional recurrent neural networks as generative models","authors":"Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, Juha T Karhunen","year":"2015","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Box et al., 2015] George EP Box, Gwilym M Jenkins, Gre- gory C Reinsel, and Greta M Ljung. Time series analysis: forecasting and control. John Wiley & Sons, 2015.","title":"Time series analysis: forecasting and control","authors":"George Ep Box, M Gwilym, Gregory C Jenkins, Greta M Reinsel, Ljung","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bright et al., 2015] JM Bright, CJ Smith, PG Taylor, and R Crook. Stochastic generation of synthetic minutely irra- diance time series derived from mean hourly weather ob- servation data. Solar Energy, 115:229-242, 2015.","title":"Stochastic generation of synthetic minutely irradiance time series derived from mean hourly weather observation data","authors":"Bright, Smith, Taylor, Crook","year":"2015","venue":"Solar Energy","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cao et al., 2018] Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. Brits: Bidirectional recurrent impu- tation for time series. In Advances in Neural Information Processing Systems, pages 6776-6786, 2018.","title":"Brits: Bidirectional recurrent imputation for time series","authors":"Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, Yitan Li","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chatfield, 2016] Chris Chatfield. The analysis of time se- ries: an introduction. CRC press, 2016.","title":"The analysis of time series: an introduction","authors":"Chris Chatfield","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Che et al., 2018] Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. Recurrent neural networks for multivariate time series with missing values. Scientific reports, 8(1):6085, 2018.","title":"Recurrent neural networks for multivariate time series with missing values","authors":"Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, Yan Liu","year":"2018","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Galbraith and Zinde-Walsh, 2001] John Galbraith and Vic- toria Zinde-Walsh. Autoregression-based estimators for arfima models. 2001.","title":"John Galbraith and Victoria Zinde-Walsh. Autoregression-based estimators for arfima models","authors":"Zinde-Walsh Galbraith","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In Advances in neural information processing systems, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Graham, 2009] John W Graham. Missing data analysis: Making it work in the real world. Annual review of psy- chology, 60:549-576, 2009.","title":"Missing data analysis: Making it work in the real world","authors":"John W, Graham","year":"2009","venue":"Annual review of psychology","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Granger and Newbold, 2014] Clive William John Granger and Paul Newbold. Forecasting economic time series. Academic Press, 2014.","title":"Forecasting economic time series","authors":"Newbold Granger, Clive William, John Granger, Paul Newbold","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hamzac ¸ebi, 2008] Cos ¸kun Hamzac ¸ebi. Improving artificial neural networks' performance in seasonal time series fore- casting. Information Sciences, 178(23):4550-4559, 2008.","title":"Cos ¸kun Hamzac ¸ebi. Improving artificial neural networks' performance in seasonal time series forecasting","authors":"Hamzac ¸ebi","year":"2008","venue":"Information Sciences","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hudak et al., 2008] Andrew T Hudak, Nicholas L Crook- ston, Jeffrey S Evans, David E Hall, and Michael J Falkowski. Nearest neighbor imputation of species-level, plot-scale forest structure attributes from lidar data. Re- mote Sensing of Environment, 112(5):2232-2245, 2008.","title":"Nearest neighbor imputation of species-level, plot-scale forest structure attributes from lidar data","authors":"Nicholas L Andrew T Hudak, Jeffrey S Crookston, David E Evans, Michael J Hall, Falkowski","year":"2008","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hyland et al., 2018] Stephanie Hyland, Cristóbal Esteban, and Gunnar Rätsch. Real-valued (medical) time series generation with recurrent conditional gans. 2018.","title":"Real-valued (medical) time series generation with recurrent conditional gans","authors":"Stephanie Hyland, Cristóbal Esteban, Gunnar Rätsch","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Johnson et al., 2012] Alistair EW Johnson, Nic Dunkley, Louis Mayaud, Athanasios Tsanas, Andrew A Kramer, and Gari D Clifford. Patient specific predictions in the in- tensive care unit using a bayesian ensemble. In Computing in Cardiology (CinC), 2012, pages 249-252. IEEE, 2012.","title":"Patient specific predictions in the intensive care unit using a bayesian ensemble","authors":"Nic Alistair Ew Johnson, Louis Dunkley, Athanasios Mayaud, Andrew A Tsanas, Gari D Kramer, Clifford","year":"2012","venue":"Computing in Cardiology (CinC)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Johnson et al., 2014] Alistair EW Johnson, Andrew A Kramer, and Gari D Clifford. Data preprocessing and mor- tality prediction: The physionet/cinc 2012 challenge re- visited. In Computing in Cardiology Conference (CinC), 2014, pages 157-160. IEEE, 2014.","title":"Data preprocessing and mortality prediction: The physionet/cinc 2012 challenge revisited","authors":"Andrew A Alistair Ew Johnson, Gari D Kramer, Clifford","year":"2014","venue":"Computing in Cardiology Conference (CinC)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Kantardzic, 2011] Mehmed Kantardzic. Data mining: con- cepts, models, methods, and algorithms. John Wiley & Sons, 2011.","title":"Mehmed Kantardzic. Data mining: concepts, models, methods, and algorithms","authors":"Kantardzic","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Luo et al., 2018] Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, et al. Multivariate time series imputa- tion with generative adversarial networks. In Advances in Neural Information Processing Systems, pages 1601- 1612, 2018.","title":"Multivariate time series imputation with generative adversarial networks","authors":"Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lv et al., 2015] Yisheng Lv, Yanjie Duan, Wenwen Kang, Zhengxi Li, Fei-Yue Wang, et al. Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intelligent Transportation Systems, 16(2):865-873, 2015.","title":"Traffic flow prediction with big data: A deep learning approach","authors":"Yisheng Lv, Yanjie Duan, Wenwen Kang, Zhengxi Li, Fei-Yue Wang","year":"2015","venue":"IEEE Trans. Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Purwar and Singh, 2015] Archana Purwar and Sandeep Ku- mar Singh. Hybrid prediction model with missing value imputation for medical data. Expert Systems with Applica- tions, 42(13):5621-5631, 2015.","title":"Hybrid prediction model with missing value imputation for medical data","authors":"Archana Purwar, Sandeep Kumar Singh","year":"2015","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sabokrou et al., 2018] Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, and Ehsan Adeli. Adversar- ially learned one-class classifier for novelty detection. In CVPR2019, pages 3379-3388, 2018.","title":"Adversarially learned one-class classifier for novelty detection","authors":"Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, Ehsan Adeli","year":"2018","venue":"CVPR2019","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Silva et al., 2012] Ikaro Silva, George Moody, Daniel J Scott, Leo A Celi, and Roger G Mark. Predict- ing in-hospital mortality of icu patients: The phys- ionet/computing in cardiology challenge 2012. Computing in cardiology, 39:245, 2012.","title":"Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge","authors":"Ikaro Silva, George Moody, J Daniel, Leo A Scott, Roger G Celi, Mark","year":"2012","venue":"Computing in cardiology","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Vincent et al., 2008] Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. Extract- ing and composing robust features with denoising autoen- coders. In Proceedings of the 25th international confer- ence on Machine learning, pages 1096-1103. ACM, 2008.","title":"Extracting and composing robust features with denoising autoencoders","authors":"Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol","year":"2008","venue":"Proceedings of the 25th international conference on Machine learning","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[White et al., 2011] Ian R White, Patrick Royston, and An- gela M Wood. Multiple imputation using chained equa- tions: issues and guidance for practice. Statistics in medicine, 30(4):377-399, 2011.","title":"Multiple imputation using chained equations: issues and guidance for practice","authors":"Patrick Ian R White, Angela M Royston, Wood","year":"2011","venue":"Statistics in medicine","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yoon et al., 2018] Jinsung Yoon, James Jordon, and Mi- haela Schaar. Gain: Missing data imputation using gen- erative adversarial nets. In International Conference on Machine Learning, pages 5675-5684, 2018.","title":"Gain: Missing data imputation using generative adversarial nets","authors":"Yoon","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}