Arrow Research search

Author name cluster

Tianfu He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

AIJ Journal 2023 Journal Article

AutoSTG+: An automatic framework to discover the optimal network for spatio-temporal graph prediction

  • Songyu Ke
  • Zheyi Pan
  • Tianfu He
  • Yuxuan Liang
  • Junbo Zhang
  • Yu Zheng

Spatio-temporal graphs (STGs) are important structures to describe urban sensory data, e. g. , traffic speed and air quality. Predicting over spatio-temporal graphs enables many essential applications in intelligent cities, such as traffic management and environment analysis. Recently, many deep learning models have been proposed for spatio-temporal graph prediction and achieved significant results. However, manually designing neural networks requires rich domain knowledge and heavy expert efforts, making it impractical for real-world deployments. Therefore, we study automated neural architecture search for spatio-temporal graphs, which meets three challenges: 1) how to define search space for capturing complex spatio-temporal correlations; 2) how to jointly model the explicit and implicit relationships between nodes of an STG; and 3) how to learn network weight parameters related to meta graphs of STGs. To tackle these challenges, we propose a novel neural architecture search framework, entitled AutoSTG+, for automated spatio-temporal graph prediction. In our AutoSTG+, spatial graph convolution and temporal convolution operations are adopted in the search space of AutoSTG+ to capture complex spatio-temporal correlations. Besides, we propose to employ the meta-learning technique to learn the adjacency matrices of spatial graph convolution layers and kernels of temporal convolution layers from the meta knowledge of meta graphs. And specifically, such meta-knowledge is learned by graph meta-knowledge learners, which iteratively aggregate knowledge on the attributed graphs and the similarity graphs. Finally, extensive experiments have been conducted on multiple real-world datasets to demonstrate that AutoSTG+ can find effective network architectures and achieve up to about 20% relative improvements compared to human-designed networks.

Details DOI

AAAI Conference 2020 Conference Paper

Learning to Generate Maps from Trajectories

  • Sijie Ruan
  • Cheng Long
  • Jie Bao
  • Chunyang Li
  • Zisheng Yu
  • Ruiyuan Li
  • Yuxuan Liang
  • Tianfu He

Accurate and updated road network data is vital in many urban applications, such as car-sharing, and logistics. The traditional approach to identifying the road network, i. e. , field survey, requires a significant amount of time and effort. With the wide usage of GPS embedded devices, a huge amount of trajectory data has been generated by different types of mobile objects, which provides a new opportunity to extract the underlying road network. However, the existing trajectory-based map recovery approaches require many empirical parameters and do not utilize the prior knowledge in existing maps, which over-simplifies or overcomplicates the reconstructed road network. To this end, we propose a deep learning-based map generation framework, i. e. , DeepMG, which learns the structure of the existing road network to overcome the noisy GPS positions. More specifically, DeepMG extracts features from trajectories in both spatial view and transition view and uses a convolutional deep neural network T2RNet to infer road centerlines. After that, a trajectory-based post-processing algorithm is proposed to re- fine the topological connectivity of the recovered map. Extensive experiments on two real-world trajectory datasets con- firm that DeepMG significantly outperforms the state-of-theart methods.

PDF Details
v2026.09.13