# Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction

arXiv: https://arxiv.org/abs/2311.12472 · HTML: https://mlsanity.com/paper/2311.12472/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 4 of 4)

- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2206.09112/) (2022)
- [Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting](https://mlsanity.com/paper/2305.13036/) (2023)
- [Understanding Urban Dynamics via Context-aware Tensor Factorization with Neighboring Regularization](https://mlsanity.com/paper/1905.00702/) (2019)

## Built on by (most cited first, 12 of 12)

- [Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting](https://mlsanity.com/paper/2506.00635/) (2025)
- [ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models](https://mlsanity.com/paper/2512.01672/) (2025)
- [STDCformer: A Transformer-Based Model with a Spatial-Temporal Causal De-Confounding Strategy for Crowd Flow Prediction](https://mlsanity.com/paper/2412.02942/) (2024)
- [Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models](https://mlsanity.com/paper/2510.17705/) (2025)
- [Bid2X: Revealing Dynamics of Bidding Environment in Online Advertising from A Foundation Model Lens](https://mlsanity.com/paper/2510.23410/) (2025)
- [HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2512.07854/) (2025)
- [Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting](https://mlsanity.com/paper/2411.11448/) (2024)
- [Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies](https://mlsanity.com/paper/2509.15481/) (2025)
- [Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding](https://mlsanity.com/paper/2511.08978/) (2025)
- [VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting](https://mlsanity.com/paper/2606.02138/) (2026)
- [Every Client Is an Environment: Federated De-confounding for Spatio-Temporal Forecasting](https://mlsanity.com/paper/2607.24218/) (2026)
- [DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning](https://mlsanity.com/paper/2609.36845/) (2026)

## Abstract (arXiv)

Traffic prediction is essential for intelligent transportation systems and urban computing. It aims to establish a relationship between historical traffic data X and future traffic states Y by employing various statistical or deep learning methods. However, the relations of X -> Y are often influenced by external confounders that simultaneously affect both X and Y , such as weather, accidents, and holidays. Existing deep-learning traffic prediction models adopt the classic front-door and back-door adjustments to address the confounder issue. However, these methods have limitations in addressing continuous or undefined confounders, as they depend on predefined discrete values that are often impractical in complex, real-world scenarios. To overcome this challenge, we propose the Spatial-Temporal sElf-superVised confoundEr learning (STEVE) model. This model introduces a basis vector approach, creating a base confounder bank to represent any confounder as a linear combination of a group of basis vectors. It also incorporates self-supervised auxiliary tasks to enhance the expressive power of the base confounder bank. Afterward, a confounder-irrelevant relation decoupling module is adopted to separate the confounder effects from direct X -> Y relations. Extensive experiments across four large-scale datasets validate our model's superior performance in handling spatial and temporal distribution shifts and underscore its adaptability to unseen confounders. Our model implementation is available at https://github.com/bigscity/STEVE_CODE.