In this paper, we investigated how to exploit the dynamic mutual influence for enhancing the prediction of social event participation. A unique characteristic of our method is that the social influence is integrated into the threshold calculation for the discriminant function, which reflects the dyn... || 用户组/社交影响;动态阈值学习;长期决定可能由于偏好、短期决定可能仅仅因为社交因素;优化函数设计类;非神经网络设计; || Tong Xu; Hui Xiong...
With the revival of neural networks, many studies try to adapt powerful sequential neural models, i.e., Recurrent Neural Networks
(RNN), to sequential recommendation. RNN-based networks encode historical interaction records into a hidden state vector. Although
the state vector is able to encode se... || 序列推荐系统+ 知识图谱; || Jin Huang...