Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning

Abstract

Time-series forecasting is one of the most active research topics in artificial intelligence. Applications in real-world time series should consider two factors for achieving reliable predictions: modeling dynamic dependencies among multiple variables and adjusting the model's intrinsic hyperparameters. A still open gap in that literature is that statistical and ensemble learning approaches systematically present lower predictive performance than deep learning methods. They generally disregard the data sequence aspect entangled with multivariate data represented in more than one time series. Conversely, this work presents a novel neural network architecture for time-series forecasting that combines the power of graph evolution with deep recurrent learning on distinct data distributions; we named our method Recurrent Graph Evolution Neural Network (ReGENN). The idea is to infer multiple multivariate relationships between co-occurring time-series by assuming that the temporal data depends not only on inner variables and intra-temporal relationships (i.e., observations from itself) but also on outer variables and inter-temporal relationships (i.e., observations from other-selves). An extensive set of experiments was conducted comparing ReGENN with dozens of ensemble methods and classical statistical ones, showing sound improvement of up to 64.87% over the competing algorithms. Furthermore, we present an analysis of the intermediate weights arising from ReGENN, showing that by looking at inter and intra-temporal relationships simultaneously, time-series forecasting is majorly improved if paying attention to how multiple multivariate data synchronously evolve.

arXiv commentIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• XGBoost: A Scalable Tree Boosting System
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• CatBoost: gradient boosting with categorical features support
• Multivariate Time series Anomaly Detection:A Framework of Hidden Markov Models
• Patient trajectory prediction in the Mimic-III dataset, challenges and pitfalls
• Change-point detection using spectral PCA for multivariate time series

Cited by in corpus (8)

• Commuting network effect on urban wealth scaling
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
• Enhancing Global Maritime Traffic Network Forecasting with Gravity-Inspired Deep Learning Models
• Spatiotemporal information conversion machine for time-series prediction
• Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning
• Multi-Path Long-Term Vessel Trajectories Forecasting with Probabilistic Feature Fusion for Problem Shifting
• Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting
• From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*