STONet: A Neural-Operator-Driven Spatio-temporal Network

• URL: http://arxiv.org/abs/2204.08414v2
• Date: Thu, 21 Apr 2022 12:35:05 GMT
• Title: STONet: A Neural-Operator-Driven Spatio-temporal Network
• Authors: Haitao Lin, Guojiang Zhao, Lirong Wu, Stan Z. Li
• Abstract summary: Graph-based graph-temporal neural networks are effective to model spatial dependency among discrete points sampled irregularly. We propose atemporal framework based on neural operators for PDEs, which learn the mechanisms governing the dynamics of spatially-continuous physical quantities. Experiments show our model's performance on forecasting spatially-continuous physic quantities, and its superior to unseen spatial points and ability to handle temporally-irregular data.
• Score: 38.5696882090282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks. However, these models are usually spatially-transductive -- only fitting the signals for discrete spatial nodes fed in models but unable to generalize to `unseen' spatial points with zero-shot. In comparison, for forecasting tasks on continuous space such as temperature prediction on the earth's surface, the \textit{spatially-inductive} property allows the model to generalize to any point in the spatial domain, demonstrating models' ability to learn the underlying mechanisms or physics laws of the systems, rather than simply fit the signals. Besides, in temporal domains, \textit{irregularly-sampled} time series, e.g. data with missing values, urge models to be temporally-continuous. Motivated by the two issues, we propose a spatio-temporal framework based on neural operators for PDEs, which learn the underlying mechanisms governing the dynamics of spatially-continuous physical quantities. Experiments show our model's improved performance on forecasting spatially-continuous physic quantities, and its superior generalization to unseen spatial points and ability to handle temporally-irregular data.

Related papers

• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Space-Time Graph Neural Networks with Stochastic Graph Perturbations [100.31591011966603]
  Space-time graph neural networks (ST-GNNs) learn efficient graph representations of time-varying data. In this paper we revisit the properties of ST-GNNs and prove that they are stable to graph stabilitys. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs.
  arXiv  Detail & Related papers  (2022-10-28T16:59:51Z)
• Continuous PDE Dynamics Forecasting with Implicit Neural Representations [24.460010868042758]
  We introduce a new data-driven, approach to PDEs flow with continuous-time dynamics of spatially continuous functions. This is achieved by embedding spatial extrapolation independently of their discretization via Implicit Neural Representations. It extrapolates at arbitrary spatial and temporal locations; it can learn sparse grids or irregular data at test time, it generalizes to new grids or resolutions.
  arXiv  Detail & Related papers  (2022-09-29T15:17:50Z)
• Scalable Spatiotemporal Graph Neural Networks [14.415967477487692]
  Graph neural networks (GNNs) are often the core component of the forecasting architecture. In most pretemporal GNNs, the computational complexity scales up to a quadratic factor with the length of the sequence times the number of links in the graph. We propose a scalable architecture that exploits an efficient encoding of both temporal and spatial dynamics.
  arXiv  Detail & Related papers  (2022-09-14T09:47:38Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)
• Space-Time Graph Neural Networks [104.55175325870195]
  We introduce space-time graph neural network (ST-GNN) to jointly process the underlying space-time topology of time-varying network data. Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs.
  arXiv  Detail & Related papers  (2021-10-06T16:08:44Z)
• Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging [3.4386226615580107]
  SATCN is a universal and flexible framework to performtemporal kriging for various datasets without need for model specification. We capture nodes by temporal convolutional networks, which allows our model to cope with data of diverse sizes. We conduct extensive experiments on three real-world datasets, including traffic and climate recordings.
  arXiv  Detail & Related papers  (2021-09-24T18:43:07Z)
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting [22.421667339552467]
  Spatial-temporal forecasting has attracted tremendous attention in a wide range of applications, and traffic flow prediction is a canonical and typical example. Existing works typically utilize shallow graph convolution networks (GNNs) and temporal extracting modules to model spatial and temporal dependencies respectively. We propose Spatial-Temporal Graph Ordinary Differential Equation Networks (STGODE), which captures spatial-temporal dynamics through a tensor-based ordinary differential equation (ODE) We evaluate our model on multiple real-world traffic datasets and superior performance is achieved over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-06-24T11:48:45Z)
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting [35.072979313851235]
  spatial-temporal data forecasting of traffic flow is a challenging task because of complicated spatial dependencies and dynamical trends of temporal pattern between different roads. Existing frameworks typically utilize given spatial adjacency graph and sophisticated mechanisms for modeling spatial and temporal correlations. This paper proposes Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting.
  arXiv  Detail & Related papers  (2020-12-15T14:03:17Z)
• On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition [97.14064057840089]
  Graphal networks (GCNs) promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a graph. Most of the recently proposed G-temporal-based methods improve the performance by learning the graph structure at each layer of the network.
  arXiv  Detail & Related papers  (2020-11-07T19:03:04Z)

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.