SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Comments: Total of 30 pages, 9 figures (4 in main, 5 in appendix), accepted to NeurIPS(Neural Information Processing Systems) 2026
Code: https://github.com/theghks3/SIMBAD
License: http://creativecommons.org/licenses/by/4.0/
The gist: Accurate traffic prediction is essential for urban planning but remains challenging due to the irregular patterns caused by unexpected events.
Abstract
Accurate traffic prediction is essential for urban planning but remains challenging due to the irregular patterns caused by unexpected events. While Spatio-Temporal Graph Neural Networks (STGNNs) effectively model periodic data, they often struggle with these aperiodic fluctuations. To address this, we propose SIMBAD, which improves generalization irregular patterns via two key mechanisms: 1) adaptive regulation of periodic signals to prioritize recent signals, and 2) dynamic spatial modeling that adjusts influence between connected nodes based on contextual relations. Built upon simple similarity metrics to adapt to aperiodic patterns, SIMBAD outperforms existing methods on real-world benchmark datasets, demonstrating superior performance in predicting unseen and irregular traffic events.
Sources
- Spectral Networks and Locally Connected Networks on Graphs
- Semi-Supervised Classification with Graph Convolutional Networks
- Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Memory Networks
- Graph WaveNet for Deep Spatial-Temporal Graph Modeling
- Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents