A Caltech Library Service

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Liu, Yukai and Yu, Rose and Zheng, Stephan and Zhan, Eric and Yue, Yisong (2019) NAOMI: Non-Autoregressive Multiresolution Sequence Imputation. In: 33rd Conference on Neural Information Processing Systems. Neural Information Processing Systems Foundation, Inc. , Art. No. 9302.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.

[img] Archive (ZIP) - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) to impute long-range sequences given arbitrary missing patterns. NAOMI exploits the multiresolution structure of spatiotemporal data and decodes recursively from coarse to fine-grained resolutions using a divide-and-conquer strategy. We further enhance our model with adversarial training. When evaluated extensively on benchmark datasets from systems of both deterministic and stochastic dynamics. NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization for long range sequences.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Yue, Yisong0000-0001-9127-1989
Additional Information:© 2019 Neural Information Processing Systems Foundation, Inc. This work was supported in part by NSF #1564330, NSF #1850349, and DARPA PAI: HR00111890035.
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)HR00111890035
Record Number:CaltechAUTHORS:20190205-100357088
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92657
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 18:11
Last Modified:09 Jul 2020 21:13

Repository Staff Only: item control page