NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

01/30/2019
by   Yukai Liu, et al.
38

Missing value imputation is a fundamental problem in modeling spatiotemporal sequences, from motion tracking to the dynamics of physical systems. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) for imputing long-range spatiotemporal sequences given arbitrary missing patterns. In particular, NAOMI exploits the multiresolution structure of spatiotemporal data to interpolate recursively from coarse to fine-grained resolutions. We further enhance our model with adversarial training using an imitation learning objective. When trained on billiards and basketball trajectories, NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60 generalization capability for long range trajectories in systems of both deterministic and stochastic dynamics.

READ FULL TEXT
research
08/07/2020

Scalable Low-Rank Autoregressive Tensor Learning for Spatiotemporal Traffic Data Imputation

Missing value problem in spatiotemporal traffic data has long been a cha...
research
03/09/2022

FragmGAN: Generative Adversarial Nets for Fragmentary Data Imputation and Prediction

Modern scientific research and applications very often encounter "fragme...
research
02/20/2023

PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation

Spatiotemporal data mining plays an important role in air quality monito...
research
05/26/2022

Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations

Modeling multivariate time series as temporal signals over a (possibly d...
research
01/11/2023

Multiple-level Point Embedding for Solving Human Trajectory Imputation with Prediction

Sparsity is a common issue in many trajectory datasets, including human ...
research
06/18/2023

Towards Stability of Autoregressive Neural Operators

Neural operators have proven to be a promising approach for modeling spa...
research
04/05/2018

Big enterprise registration data imputation: Supporting spatiotemporal analysis of industries in China

Big, fine-grained enterprise registration data that includes time and lo...

Please sign up or login with your details

Forgot password? Click here to reset