no code implementations • 11 Mar 2024 • Dong Chen, Shuai Zheng, Muhao Xu, Zhenfeng Zhu, Yao Zhao
In the domain of dynamic graph representation learning (DGRL), the efficient and comprehensive capture of temporal evolution within real-world networks is crucial.
no code implementations • 23 Apr 2022 • Muhao Xu, Xueying Zhou, Xizhan Gao, WeiKai He, Sijie Niu
Specifically, we firstly design a gradient preference based selector to store powerful feature points in space and then construct a feature repository, which alleviate the interference of redundant feature vectors and improve inference efficiency.