Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
Not on the map. Why?
Abstract (arXiv)
Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions--both direct and indirect. To confront these complexities, we introduce a method of representing multivariate signals as nodes in a graph with edges indicating interdependency between them. Specifically, we leverage graph neural networks (GNN) and attention mechanisms to efficiently learn the underlying relationships within the time series data. Moreover, we suggest employing hierarchical signal decompositions running over the graphs to capture multiple spatial dependencies. The effectiveness of our proposed model is evaluated across various real-world benchmark datasets designed for long-term forecasting tasks. The results consistently showcase the superiority of our model, achieving an average 23% reduction in mean squared error (MSE) compared to existing models.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 21 Nov 2023.
Builds on
28 of 37 references.
References · 28
- 2017Attention Is All You Needcited by 60,361
- 2020Longformer: The Long-Document Transformercited by 3,413
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
- 2020Reformer: The Efficient Transformercited by 1,668
- 2019Generating Long Sequences with Sparse Transformerscited by 1,546
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
- 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
16 more
- 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
- 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
- 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
- 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
- 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
- 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
- 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
- 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
- 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
- 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
- 2017Long-term Forecasting using Higher Order Tensor RNNscited by 34
- 2020Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 18
- 2022Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networkscited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.