1 code implementation • journal 2024 • Jin Fan, Wenchao Weng, Hao Tian, Huifeng Wu, Fu Zhu, Jia Wu
RGDAN comprises a graph diffusion attention module and a temporal attention module.
Ranked #1 on Traffic Prediction on NE-BJ
1 code implementation • IEEE Transactions on Emerging Topics in Computing 2022 • Jin Fan, Zehao Wang, Danfeng Sun, Huifeng Wu
These include: 1) complexity - Informer has a relatively high computational complexity and a high memory overhead; 2) nuance - there is limited ability to capture the subtle features in a data stream; 3) interpretability - the inference procedure of Informer is not explainable; 4) extensibility - accuracy is poor with extra-long multivariate time series.
1 code implementation • Future Generation Computer Systems 2022 • Zehao Wang, Huifeng Wu, Jin Fan, Danfeng Sun, Jia Wu
Heterogeneous graph embedding is a crucial step in HGNNs.
no code implementations • 13 Mar 2022 • Ke Zhang, Jin Fan, Shaoli Huang, Yongliang Qiao, Xiaofeng Yu, Feiwei Qin
We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem.