AutoSTL: Automated Spatio-Temporal Multi-Task Learning

TL;DR

AutoSTL is a novel automated multi-task learning framework that effectively models complex spatio-temporal dependencies and relationships between multiple tasks, achieving state-of-the-art results in smart city prediction scenarios.

Contribution

It introduces the first automated approach for joint spatio-temporal multi-task learning with a scalable architecture and automatic operation and fusion weight allocation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively captures complex spatio-temporal dependencies.

Automatically allocates operations and fusion weights.

Abstract

Spatio-Temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing studies fail to address this joint learning problem well, which generally solve tasks individually or a fixed task combination. The challenges lie in the tangled relation between different properties, the demand for supporting flexible combinations of tasks and the complex spatio-temporal dependency. To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly. Firstly, we propose a scalable architecture consisting of advanced spatio-temporal operations to exploit the complicated dependency. Shared modules and feature fusion mechanism are incorporated to further capture the intrinsic relationship between tasks. Furthermore, our model automatically allocates the operations and fusion weight. Extensive experiments on benchmark datasets verified that our model achieves state-of-the-art performance. As we can know, AutoSTL is the first automated spatio-temporal multi-task learning method.