no code implementations • 2 Jan 2024 • Li Sun, Junda Ye, Jiawei Zhang, Yong Yang, Mingsheng Liu, Feiyang Wang, Philip S. Yu
To address the aforementioned issues, we propose a novel Contrastive model for Sequential Interaction Network learning on Co-Evolving RiEmannian spaces, CSINCERE.
1 code implementation • 31 Oct 2023 • Liang Liao, Liang Wan, Mingsheng Liu, Shusheng Li
To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion.