Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

  title={Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs},
  author={Ming Jin and Yu Zheng and Yuanhao Li and Siheng Chen and B. Yang and Shirui Pan},
—Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, they have three fundamental limitations. (i). Discrete neural architectures : Interlacing individually parameterized spatial and temporal blocks to encode rich underlying patterns leads to discontinuous latent state trajectories and higher forecasting numerical errors. (ii). High… 

Figures and Tables from this paper

TraverseNet: Unifying Space and Time in Message Passing

This article aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial-temporal dependencies for traffic data by proposing TraverseNet, a novel spatial- Temporal graph neural network, viewing space and time as an inseparable whole.

Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting

A novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from interaction modules is proposed, and a general CU-aware regression framework with an original permutation-equivariant uncertainty estimator is built to do both tasks of regression and uncertainty estimation.

Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination

Graph contrastive learning (GCL) alleviates the heavy reliance on label information for graph representation learning (GRL) via self-supervised learning schemes. The core idea is to learn by

Projective Ranking-based GNN Evasion Attacks

The perturbation space is formulated and an evaluation framework and the projective ranking method is proposed, which aims to learn a powerful attack strategy then adapt it as little as possible to generate adversarial samples under dynamic budget settings.

Unifying Graph Contrastive Learning with Flexible Contextual Scopes

The architecture of UGCL can be considered as a general framework to unify existing GCL methods and builds flexible contextual representations with tunable contextual scopes by controlling the power of an adjacency matrix.



Discrete Graph Structure Learning for Forecasting Multiple Time Series

This work proposes learning the structure simultaneously with the GNN if the graph is unknown, and casts the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution.

Modeling Temporal Patterns with Dilated Convolutions for Time-Series Forecasting

The proposed HyDCNN is a novel hybrid framework based on fully Dilated CNN for time-series forecasting tasks, in which the proposed position-aware dilated CNNs are utilized to capture the sequential non-linear dynamics and an autoregressive model is leveraged to captured the sequential linear dependencies.

Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

A novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge of multivariate time series forecasting, using the Convolution Neural Network and the Recurrent Neural Network to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends.

Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

This work proposes Spatial-Temporal Graph Ordinary Differential Equation Networks (STGODE), which captures spatial-temporal dynamics through a tensor-based ordinary differential equation (ODE), as a result, deeper networks can be constructed and spatial- Temporal features are utilized synchronously.

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow and evaluates the framework on two real-world large scale road network traffic datasets and observes consistent improvement.

Graph Neural Network for Traffic Forecasting: A Survey

Forecasting energy time series with profile neural networks

The proposed deep neural network architecture outperforms current state-of-the-art deep learning benchmark models regarding the forecasting accuracy on forecast horizons of one day and one week-ahead, improving the mean absolute scaled error by up to 25%, as well as regarding the trade-off between training time and accuracy.

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

An efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: a ProbSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences' dependency alignment.

Graph Neural Controlled Differential Equations for Traffic Forecasting

The method of spatio-temporal graph neural controlled differential equation (STG-NCDE) shows the best accuracy in all cases, outperforming all those 20 baselines by non-trivial margins.

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

This paper proposes a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain, and builds the model with complete convolutional structures, which enable much faster training speed with fewer parameters.