Tian Shu
2 Papers
Tian Shu is an academic researcher. The author has contributed to research in topics: Flow network & Computer science. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization.
Xiaokang Zhou,Xuzhe Zheng,Tian Shu,Wei Liang,Kevin I-Kai Wang,Lianyong Qi,Shohei Shimizu,Qun Jin +7 more
TL;DR: A deep generative model framework is introduced, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms.
38
Graph Attention Network With Spatial-Temporal Clustering for Traffic Flow Forecasting in Intelligent Transportation System
Yan Chen,Tian Shu,Xiaokang Zhou,Xuzhe Zheng,Akira Kawai,Kaoru Fueda,Zheng Yan,Wei Liang,Kevin I-Kai Wang +8 more
TL;DR: This paper proposes a Graph Attention Network with Spatial-Temporal Clustering (GAT-STC), which considers the so-called recent-aware features and periodic- aware features, to improve the Graph Neural Network (GNN)-based traffic flow forecasting in Intelligent Transportation System (ITS).
17