Long-Range Transformers for Dynamic Spatiotemporal Forecasting
arXiv:2109.12218
Abstract
Multivariate time series forecasting focuses on predicting future values based on historical context. State-of-the-art sequence-to-sequence models rely on neural attention between timesteps, which allows for temporal learning but fails to consider distinct spatial relationships between variables. In contrast, methods based on graph neural networks explicitly model variable relationships. However, these methods often rely on predefined graphs that cannot change over time and perform separate spatial and temporal updates without establishing direct connections between each variable at every timestep. Our work addresses these problems by translating multivariate forecasting into a "spatiotemporal sequence" formulation where each Transformer input token represents the value of a single variable at a given time. Long-Range Transformers can then learn interactions between space, time, and value information jointly along this extended sequence. Our method, which we call Spacetimeformer, achieves competitive results on benchmarks from traffic forecasting to electricity demand and weather prediction while learning spatiotemporal relationships purely from data.
References in corpus (13)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Linformer: Self-Attention with Linear Complexity
- Generating Long Sequences with Sparse Transformers
- Reducing Transformer Depth on Demand with Structured Dropout
- Long Range Arena: A Benchmark for Efficient Transformers
- Rethinking Attention with Performers
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
- Long-Short Transformer: Efficient Transformers for Language and Vision
- BP-Transformer: Modelling Long-Range Context via Binary Partitioning
- Time2Vec: Learning a Vector Representation of Time
- Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
- Few-shot Learning for Time-series Forecasting
- UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost