Graph correlated attention recurrent neural network for multivariate time series forecasting

Geng, Xiulin; He, Xiaoyu; Xu, Lingyu; Yu, Jie

doi:10.1016/j.ins.2022.04.045

Cited by 43 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Great effort is put into developing effective techniques to model incomplete graph data. For instance, an adaptive graph recurrent network has been proposed, which combines graph and RNNs for air quality and traffic data imputation [29]. To model temporal session data in discrete state spaces, a graph nested GRU ODE model is proposed to preserve the continuous nature of dynamic user preferences, where a graph gated neural network is employed to encode both temporal and structural patterns for inferring initial latent states and a time alignment algorithm is designed to align the updating time steps of temporal session graphs [30].…”

Section: One-stage Methodsmentioning

confidence: 99%

Time-aware neural ordinary differential equations for incomplete time series modeling

et al. 2023

View full text Add to dashboard Cite

Internet of Things realizes the ubiquitous connection of all things, generating countless time-tagged data called time series. However, real-world time series are often plagued with missing values on account of noise or malfunctioning sensors. Existing methods for modeling such incomplete time series typically involve preprocessing steps, such as deletion or missing data imputation using statistical learning or machine learning methods. Unfortunately, these methods unavoidable destroy time information and bring error accumulation to the subsequent model. To this end, this paper introduces a novel continuous neural network architecture, named Time-aware Neural-Ordinary Differential Equations (TN-ODE), for incomplete time data modeling. The proposed method not only supports imputation missing values at arbitrary time points, but also enables multi-step prediction at desired time points. Specifically, TN-ODE employs a time-aware Long Short-Term Memory as an encoder, which effectively learns the posterior distribution from partial observed data. Additionally, the derivative of latent states is parameterized with a fully connected network, thereby enabling continuous-time latent dynamics generation. The proposed TN-ODE model is evaluated on both real-world and synthetic incomplete time-series datasets by conducting data interpolation and extrapolation tasks as well as classification task. Extensive experiments show the TN-ODE model outperforms baseline methods in terms of Mean Square Error for imputation and prediction tasks, as well as accuracy in downstream classification task.

show abstract

Section: One-stage Methodsmentioning

confidence: 99%

Time-aware neural ordinary differential equations for incomplete time series modeling

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Recent studies have bridged this gap by combining GNNs with Recurrent Neural Networks (RNNs), exploring the interplay of spatial and temporal changes 37 and achieving promising results. The advent of Encoder-Decoder architectures, renowned for their efficacy in processing sequential data 38 , has further propelled innovations in TSF.…”

Section: Forecastingmentioning

confidence: 99%

From Data to Action: Flood Forecasting Leveraging Graph Neural Networks and Digital Twin Visualization

Roudbari,

Punekar,

Patterson

et al. 2024

Preprint

View full text Add to dashboard Cite

Forecasting floods encompasses significant complexity due to the nonlinear nature of hydrological systems, which involve intricate interactions among precipitation, landscapes, river systems, and hydrological networks. Recent efforts in hydrology have aimed at predicting water flow, floods, and quality, yet most methodologies overlook the influence of adjacent areas and lack advanced visualization for water level assessment. Our contribution is twofold: firstly, we introduce a graph neural network model equipped with a graph learning module to capture the interconnections of water systems and the connectivity between stations to predict future water levels. Secondly, we develop a simulation prototype offering visual insights for decision-making in disaster prevention and policy-making. This prototype visualizes predicted water levels and facilitates data analysis using decades of historical information. Focusing on the Greater Montreal Area (GMA), particularly Terrebonne, Quebec, Canada, we apply our model and prototype to demonstrate a comprehensive method for assessing flood impacts. By utilizing a digital twin of Terrebonne, our simulation tool allows users to interactively modify the landscape and simulate various flood scenarios, thereby providing valuable insights into preventive strategies. This research aims to enhance water level prediction and evaluation of preventive measures, setting a benchmark for similar applications across different geographic areas.

show abstract

“…GATs introduced a self-attention mechanism that assigns different weights to each node in the graph based on its neighbor node features while computing its representation. For instance, frameworks such as GAT-LSTM [ 36 ], TC-GATN [ 37 ], and GCAR [ 38 ] utilize attention graph networks to model intricate and dynamic spatial correlations, leading to improved prediction performance. The advantage of GATs lies in their ability to train without requiring knowledge of the entire graph structure; only the neighboring nodes of each node are considered, leading to parallel computation on different nodes and fast computation speed.…”

Section: Related Workmentioning

confidence: 99%

Multi-Task Time Series Forecasting Based on Graph Neural Networks

Han,

Huang,

Pan

et al. 2023

Entropy

View full text Add to dashboard Cite

Accurate time series forecasting is of great importance in real-world scenarios such as health care, transportation, and finance. Because of the tendency, temporal variations, and periodicity of the time series data, there are complex and dynamic dependencies among its underlying features. In time series forecasting tasks, the features learned by a specific task at the current time step (such as predicting mortality) are related to the features of historical timesteps and the features of adjacent timesteps of related tasks (such as predicting fever). Therefore, capturing dynamic dependencies in data is a challenging problem for learning accurate future prediction behavior. To address this challenge, we propose a cross-timestep feature-sharing multi-task time series forecasting model that can capture global and local dynamic dependencies in time series data. Initially, the global dynamic dependencies of features within each task are captured through a self-attention mechanism. Furthermore, an adaptive sparse graph structure is employed to capture the local dynamic dependencies inherent in the data, which can explicitly depict the correlation between features across timesteps and tasks. Lastly, the cross-timestep feature sharing between tasks is achieved through a graph attention mechanism, which strengthens the learning of shared features that are strongly correlated with a single task. It is beneficial for improving the generalization performance of the model. Our experimental results demonstrate that our method is significantly competitive compared to baseline methods.

show abstract

Graph correlated attention recurrent neural network for multivariate time series forecasting

Cited by 43 publications

References 32 publications

Time-aware neural ordinary differential equations for incomplete time series modeling

Time-aware neural ordinary differential equations for incomplete time series modeling

From Data to Action: Flood Forecasting Leveraging Graph Neural Networks and Digital Twin Visualization

Multi-Task Time Series Forecasting Based on Graph Neural Networks

Contact Info

Product

Resources

About