Timezone: »
Time series are widely used as signals in many classification/regression tasks. It is ubiquitous that time series contains many missing values. Given multiple correlated time series data, how to fill in missing values and to predict their class labels? Existing imputation methods often impose strong assumptions of the underlying data generating process, such as linear dynamics in the state space. In this paper, we propose BRITS, a novel method based on recurrent neural networks for missing value imputation in time series data. Our proposed method directly learns the missing values in a bidirectional recurrent dynamical system, without any specific assumption. The imputed values are treated as variables of RNN graph and can be effectively updated during the backpropagation. BRITS has three advantages: (a) it can handle multiple correlated missing values in time series; (b) it generalizes to time series with nonlinear dynamics underlying; (c) it provides a data-driven imputation procedure and applies to general settings with missing data. We evaluate our model on three real-world datasets, including an air quality dataset, a health-care data, and a localization data for human activity. Experiments show that our model outperforms the state-of-the-art methods in both imputation and classification/regression accuracies.
Author Information
Wei Cao (Tsinghua University)
Dong Wang (Duke University)
Jian Li (Tsinghua University)
Hao Zhou (Bytedance AI Lab)
Lei Li (ByteDance AI Lab)
Yitan Li (ByteDance.Inc)
More from the Same Authors
-
2022 Poster: Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability »
Zixuan Wang · Zhouzi Li · Jian Li -
2022 Poster: Generalization Bounds for Gradient Methods via Discrete and Continuous Prior »
Xuanyuan Luo · Bei Luo · Jian Li -
2022 Poster: Zero-Shot 3D Drug Design by Sketching and Generating »
Siyu Long · Yi Zhou · Xinyu Dai · Hao Zhou -
2022 Spotlight: Lightning Talks 2A-4 »
Sarthak Mittal · Richard Grumitt · Zuoyu Yan · Lihao Wang · Dongsheng Wang · Alexander Korotin · Jiangxin Sun · Ankit Gupta · Vage Egiazarian · Tengfei Ma · Yi Zhou · Yishi Xu · Albert Gu · Biwei Dai · Chunyu Wang · Yoshua Bengio · Uros Seljak · Miaoge Li · Guillaume Lajoie · Yiqun Wang · Liangcai Gao · Lingxiao Li · Jonathan Berant · Huang Hu · Xiaoqing Zheng · Zhibin Duan · Hanjiang Lai · Evgeny Burnaev · Zhi Tang · Zhi Jin · Xuanjing Huang · Chaojie Wang · Yusu Wang · Jian-Fang Hu · Bo Chen · Chao Chen · Hao Zhou · Mingyuan Zhou -
2022 Spotlight: Zero-Shot 3D Drug Design by Sketching and Generating »
Siyu Long · Yi Zhou · Xinyu Dai · Hao Zhou -
2022 Spotlight: Regularized Molecular Conformation Fields »
Lihao Wang · Yi Zhou · Yiqun Wang · Xiaoqing Zheng · Xuanjing Huang · Hao Zhou -
2022 Poster: Regularized Molecular Conformation Fields »
Lihao Wang · Yi Zhou · Yiqun Wang · Xiaoqing Zheng · Xuanjing Huang · Hao Zhou -
2022 Poster: Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation »
Jin Xu · Xiaojiang Liu · Jianhao Yan · Deng Cai · Huayang Li · Jian Li -
2019 Poster: On Fenchel Mini-Max Learning »
Chenyang Tao · Liqun Chen · Shuyang Dai · Junya Chen · Ke Bai · Dong Wang · Jianfeng Feng · Wenlian Lu · Georgiy Bobashev · Lawrence Carin -
2016 Poster: Combinatorial Multi-Armed Bandit with General Reward Functions »
Wei Chen · Wei Hu · Fu Li · Jian Li · Yu Liu · Pinyan Lu