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

arXiv: https://arxiv.org/abs/2008.12833 · HTML: https://mlsanity.com/paper/2008.12833/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2020.

## Built on by (most cited first, 22 of 22)

- [TACTiS: Transformer-Attentional Copulas for Time Series](https://mlsanity.com/paper/2202.03528/) (2022)
- [A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting](https://mlsanity.com/paper/2109.01657/) (2021)
- [Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation](https://mlsanity.com/paper/2107.00946/) (2021)
- [Multi-Path Long-Term Vessel Trajectories Forecasting with Probabilistic Feature Fusion for Problem Shifting](https://mlsanity.com/paper/2310.18948/) (2023)
- [Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective](https://mlsanity.com/paper/2301.11535/) (2023)
- [Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2209.00654/) (2022)
- [Enhancing Global Maritime Traffic Network Forecasting with Gravity-Inspired Deep Learning Models](https://mlsanity.com/paper/2401.13098/) (2024)
- [Spatiotemporal information conversion machine for time-series prediction](https://mlsanity.com/paper/2107.01353/) (2021)
- [Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning](https://mlsanity.com/paper/2202.13867/) (2022)
- [SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting](https://mlsanity.com/paper/2503.02836/) (2025)
- [Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection](https://mlsanity.com/paper/2201.04792/) (2022)
- [Curricular and Cyclical Loss for Time Series Learning Strategy](https://mlsanity.com/paper/2312.15853/) (2023)
- [Integrating Quantum-Classical Attention in Patch Transformers for Enhanced Time Series Forecasting](https://mlsanity.com/paper/2504.00068/) (2025)
- [An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis](https://mlsanity.com/paper/2604.02502/) (2026)
- [From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*](https://mlsanity.com/paper/2206.01176/) (2022)
- [Myopia prediction for adolescents via time-aware deep learning](https://mlsanity.com/paper/2209.12546/) (2022)
- [Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data](https://mlsanity.com/paper/2211.16653/) (2022)
- [Probabilistic Learning of Multivariate Time Series with Temporal Irregularity](https://mlsanity.com/paper/2306.09147/) (2023)
- [VN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting](https://mlsanity.com/paper/2404.16037/) (2024)
- [Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting](https://mlsanity.com/paper/2510.23656/) (2025)
- [Spatio-temporal stochastic graph-based learning for infectious disease forecasting](https://mlsanity.com/paper/2605.30662/) (2026)
- [Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning](https://mlsanity.com/paper/2608.29012/) (2026)

## Abstract (arXiv)

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.