DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models

• URL: http://arxiv.org/abs/2301.13629v4
• Date: Sun, 10 Mar 2024 01:31:24 GMT
• Title: DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models
• Authors: Haomin Wen, Youfang Lin, Yutong Xia, Huaiyu Wan, Qingsong Wen, Roger Zimmermann, Yuxuan Liang
• Abstract summary: This paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex dependencies. We present the first attempt to generalize the popular denoising diffusion models to STGs, leading to a novel non-autoregressive framework called DiffSTG. Our approach combines the intrinsic-temporal learning capabilities STNNs with the uncertainty measurements of diffusion models.
• Score: 53.67562579184457
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model [45.45700202300292]
  CaPaint aims to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts. Experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%.
  arXiv  Detail & Related papers  (2024-09-29T08:18:50Z)
• STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model [11.211981320116323]
  We introduce Spatial-Temporal Graph Mamba (STG-Mamba) as the first exploration of leveraging the powerful selective state space models for STG learning. STG-Mamba treats STG Network as a system, and meticulously explore the STG system's dynamic state evolution across temporal dimension. It not only surpasses existing state-of-the-art methods in terms of STG forecasting performance, but also effectively alleviate the computational bottleneck of large-scale graph networks.
  arXiv  Detail & Related papers  (2024-03-19T04:02:57Z)
• Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment [33.4989883914555]
  We propose a novel framework called CaST to tackle temporal out-of-distribution issues and dynamic spatial causation. Experiments results on three real-world datasets demonstrate the effectiveness and practicality of CaST.
  arXiv  Detail & Related papers  (2023-09-23T13:51:09Z)
• Exploring the Relationship between Samples and Masks for Robust Defect Localization [1.90365714903665]
  This paper proposes a one-stage framework that detects defective patterns directly without the modeling process. Explicit information that could indicate the position of defects is intentionally excluded to avoid learning any direct mapping. Results show that the proposed method is 2.9% higher than the SOTA methods in F1-Score, while substantially outperforming SOTA methods in generalizability.
  arXiv  Detail & Related papers  (2023-06-19T06:41:19Z)
• Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
  Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
  arXiv  Detail & Related papers  (2021-10-20T14:23:54Z)
• Cloud Failure Prediction with Hierarchical Temporary Memory: An Empirical Assessment [64.73243241568555]
  Hierarchical Temporary Memory (HTM) is an unsupervised learning algorithm inspired by the features of the neocortex. This paper presents the first systematic study that assesses HTM in the context of failure prediction.
  arXiv  Detail & Related papers  (2021-10-06T07:09:45Z)
• Spatio-Temporal Graph Contrastive Learning [49.132528449909316]
  We propose a Spatio-Temporal Graph Contrastive Learning framework (STGCL) to tackle these issues. We elaborate on four types of data augmentations which disturb data in terms of graph structure, time domain, and frequency domain. Our framework is evaluated across three real-world datasets and four state-of-the-art models.
  arXiv  Detail & Related papers  (2021-08-26T16:05:32Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Spatio-Temporal Graph Scattering Transform [54.52797775999124]
  Graph neural networks may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data. We put forth a novel mathematically designed framework to analyze-temporal data.
  arXiv  Detail & Related papers  (2020-12-06T19:49:55Z)
• Spatiotemporal Adaptive Neural Network for Long-term Forecasting of Financial Time Series [0.2793095554369281]
  We investigate whether deep neural networks (DNNs) can be used to forecast time series (TS) forecasts conjointly. We make use of the dynamic factor graph (DFG) to build a multivariate autoregressive model. With ACTM, it is possible to vary the autoregressive order of a TS model over time and model a larger set of probability distributions.
  arXiv  Detail & Related papers  (2020-03-27T00:53:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.