TrajGRU-Attention-ODE: Novel Spatiotemporal Predictive Models

Quang Nguyen Tri Le, Francois Chan, Claude D'Amours

Keywords: Spatiotemporal predictive model, convolutional recurrent neural network, attention mechanism, neural ordinary differential equation, irregularly sampled time series.

TL;DR: This paper presents novel deep learning models for spatiotemporal predictive tasks.

Abstract: To perform the long-term spatiotemporal sequence prediction (SSP) task with irregular time sampling assumptions, we build the sequence-to-sequence models based on the Trajectory Gated Recurrent Unit (TrajGRU) network and our proposed deep learning modules. First, we design a novel attention mechanism, namely Motion-based Attention (MA), and insert it into the TrajGRU network to create the TrajGRU-Attention model. In particular, the TrajGRU-Attention model can alleviate the impact of the vanishing gradient, which leads to the blurry effect in the long-term predictions and handle both regularly sampled and irregularly sampled time series. Second, leveraging the advances in Neural Ordinary Differential Equation (NODE) technique, we proposed the TrajGRU-Attention-ODE model, which can be applied in continuous-time applications. To evaluate the performance of the proposed models, we select three available spatiotemporal datasets based on the complexity level, including the MovingMNIST, MovingMNIST++, and KTH Action. Our models outperform the state-of-the-art NODE model and generate better results than the standard TrajGRU model for SSP tasks with different circumstances of time sampling.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning