Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

Yutong Xia · Yuxuan Liang · Haomin Wen · Xu Liu · Kun Wang · Zhengyang Zhou · Roger Zimmermann

Great Hall & Hall B1+B2 (level 1) #435
[ ] [ Project Page ]
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST


Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments. Concretely, leveraging a causal lens, we first build a structural causal model to decipher the data generation process of STGs. To handle the temporal OoD issue, we employ the back-door adjustment by a novel disentanglement block to separate the temporal environments from input data. Moreover, we utilize the front-door adjustment and adopt edge-level convolution to model the ripple effect of causation. Experiments results on three real-world datasets demonstrate the effectiveness of CaST, which consistently outperforms existing methods with good interpretability. Our source code is available at

Chat is not available.