Can I read Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting on EtoBox?

Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting by Wang, Hongjun; Chen, Jiyuan; Zhang, Lingyu; Jiang, Renhe; Song, Xuan is a scholarly article available to read on EtoBox.

What is Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting about?

Spatiotemporal Graph Neural Networks (ST-GNNs) and Transformers have shown significant promise in traffic forecasting by effectively modeling temporal and spatial correlations. However, rapid urbanization in recent years has led to dynamic shifts in traffic patterns and travel demand, posing major challenges for accurate long-term traffic prediction. The generalization capability of ST-GNNs in extended temporal scenarios and cross-city applications remains largely unexplored. In this study, we evaluate state-of-the-art models on an extended traffic benchmark and observe substantial performance degradation in existing ST-GNNs over time, which we attribute to their limited inductive capabilities. Our analysis reveals that this degradation stems from an inability to adapt to evolving spatial relationships within urban environments. To address this limitation, we reconsider the design of adaptive embeddings and propose a Principal Component Analysis (PCA) embedding approach that enables models to adapt to new scenarios without retraining. We incorporate PCA embeddings into existing ST-GNN and Transformer architectures, achieving marked improvements in performance. Notably, PCA embeddin

Author

Wang, Hongjun; Chen, Jiyuan; Zhang, Lingyu; Jiang, Renhe; Song, Xuan

Published

2024

Language

EN