Spatio-temporal graph neural networks (STGNN) have emerged as the dominant model for spatio-temporal graph (STG) forecasting. Despite their success, they fail to model intrinsic uncertainties within STG data, which cripples their practicality in downstream tasks for decision-making. To this end, this paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex ST dependencies. In this study, we present the first attempt to generalize the popular denoising diffusion probabilistic models to STGs, leading to a novel non-autoregressive framework called DiffSTG, along with the first denoising network UGnet for STG in the framework. Our approach combines the spatio-temporal learning capabilities of STGNNs with the uncertainty measurements of diffusion models. Extensive experiments validate that DiffSTG reduces the Continuous Ranked Probability Score (CRPS) by 4%-14%, and Root Mean Squared Error (RMSE) by 2%-7% over existing methods on three real-world datasets.
翻译:Spatio-时间图神经网络(STGNN)已成为时空图预测的主要模型。 尽管它们取得了成功, 它们未能在STG数据中模拟内在的不确定性, 从而削弱其下游决策任务的实际性。 为此, 本文件侧重于概率性STG预测, 由于在模拟不确定性和复杂的依赖性方面的困难,这种预测具有挑战性。 在本研究中, 我们首次尝试将流行的去知性扩散概率模型推广到STG, 从而形成一个名为 DiffSTG 的新颖的非航空性框架, 以及这个框架中第一个STG的去知性网络 UGnet。 我们的方法将STGNNs的时空学习能力与扩散模型的不确定性测量结合起来。 广泛的实验证实DiffSTG 将连续排名概率降4%至14%, 根位平方错误(RMSE) 比三个现实世界数据集的现有方法减少2%至7%。