# Do We Really Need Adaptive Global Spatial Attention for Traffic Forecasting?

arXiv: https://arxiv.org/abs/2607.12462 · HTML: https://mlsanity.com/paper/2607.12462/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2106.12931/) (2021)
- [Spatial-Temporal Transformer Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2001.02908/) (2020)
- [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2208.05233/) (2022)
- [PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2301.07945/) (2023)
- [Graph Neural Controlled Differential Equations for Traffic Forecasting](https://mlsanity.com/paper/2112.03558/) (2021)
- [FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting](https://mlsanity.com/paper/2007.15531/) (2020)
- [Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective](https://mlsanity.com/paper/2412.09972/) (2024)
- [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https://mlsanity.com/paper/2309.13363/) (2023)
- [Do We Really Need Graph Neural Networks for Traffic Forecasting?](https://mlsanity.com/paper/2301.12603/) (2023)
- [Scratching Visual Transformer's Back with Uniform Attention](https://mlsanity.com/paper/2210.08457/) (2022)
- [STD-PLM: Understanding Both Spatial and Temporal Properties of Spatial-Temporal Data with PLM](https://mlsanity.com/paper/2407.09096/) (2024)
- [Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks](https://mlsanity.com/paper/2401.15894/) (2024)

## Built on by (most cited first, 1 of 1)

- [Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention](https://mlsanity.com/paper/2610.01831/) (2026)

## Abstract (arXiv)

Existing traffic forecasting models commonly focus on extracting spatial dependencies, particularly global spatial information, which characterizes the representations obtained through interactions between each node and all nodes across the traffic network. However, the underlying mechanism by which global information is modeled and extracted remains insufficiently investigated. Whether global information must be extracted by high-degree-of-freedom adaptive attention or can be captured by a simple global aggregation operator remains unclear. For this purpose, we design a controlled ablation framework that replaces only the spatial mixing module to test attention-based global interaction. Across six traffic benchmarks, standard spatial attention yields relative MAE changes of -1.58% to +1.26% compared with uniform full-range mixing, and we observe no consistent advantage for standard spatial attention, while uniform full-range mixing reduces node-scale spatial-mixing complexity from O(N2) to O(N). We further propose a hypothesized model that decomposes spatial attention into a row-uniform global background and a non-uniform residual. The residual shows dataset-dependent effects. Overall, uniform full-range mixing provides a strong global spatial baseline, while the non-uniform attention residual is not consistently beneficial across datasets.