Timezone: »

 
Poster
AutoST: Towards the Universal Modeling of Spatio-temporal Sequences
Jianxin Li · Shuai Zhang · Hui Xiong · Haoyi Zhou

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #627
in Poster Session 5 »

The analysis of spatio-temporal sequences plays an important role in many real-world applications, demanding a high model capacity to capture the interdependence among spatial and temporal dimensions. Previous studies provided separated network design in three categories: spatial first, temporal first, and spatio-temporal synchronous. However, the manually-designed heterogeneous models can hardly meet the spatio-temporal dependency capturing priority for various tasks. To address this, we proposed a universal modeling framework with three distinctive characteristics: (i) Attention-based network backbone, including S2T Layer (spatial first), T2S Layer (temporal first), and STS Layer (spatio-temporal synchronous). (ii) The universal modeling framework, named UniST, with a unified architecture that enables flexible modeling priorities with the proposed three different modules. (iii) An automatic search strategy, named AutoST, automatically searches the optimal spatio-temporal modeling priority by network architecture search. Extensive experiments on five real-world datasets demonstrate that UniST with any single type of our three proposed modules can achieve state-of-the-art performance. Furthermore, AutoST can achieve overwhelming performance with UniST.

Keywords: Neural Network · Architecture Search · Spatio-temporal Forecasting
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Jianxin Li (Beihang University)
Shuai Zhang (Beihang University)
Hui Xiong (Hong Kong University of Science and Technology )
Haoyi Zhou (Beihang University)

More from the Same Authors