Futong Zhuo

Futong Zhuo

Auto-generated profile, based on publicly available information

Futong Zhuo

College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 September 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
JZJianli Zhao
Jianli Zhao
FZFutong Zhuo
Futong Zhuo
QSQiu-xia Sun
Qiu-xia Sun
QLQing Li
Qing Li
YHYiran Hua
Yiran Hua
JZJianye Zhao
Jianye Zhao
Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic patterns. Previous works captured spatial dependencies based on graph neural networks and used fixed graph construction methods to characterize spatial relationships, which limits the ability of models to capture dynamic and long-range spatial dependencies. Meanwhile, prior studies did not consider the issue of a large number of redundant parameters in traffic prediction models, which not only increases the storage cost of the model but also reduces its generalization ability. To address the above challenges, we propose a Dynamic Spatial Transformer for Traffic Forecasting with Low-Rank Tensor Compression (DSFormer-LRTC). Specifically, we constructed a global spatial Transformer to capture remote spatial dependencies, and a distance-based mask matrix is used in local spatial Transformer to enhance the adjacent spatial influence. To reduce the complexity of the model, the model adopts a design that separates temporal and spatial. Meanwhile, we introduce low-rank tensor decomposition to reconstruct the parameter matrix in Transformer module to compress the proposed model. Experimental results show that DSFormer-LRTC achieves state-of-the-art performance on four real-world datasets. The experimental analysis of attention matrix also proves that the model can learn dynamic and distant spatial features. Finally, the compressed model parameters reduce the original parameter size by two-thirds, while significantly outperforming the baseline model in terms of computational efficiency.