Siamese learning based on graph differential equation for Next-POI recommendation

Yuxuan Yang, Siyuan Zhou, He Weng, Dongjing Wang, Xin Zhang, Dongjin Yu, Shuiguang Deng

Abstract: Highlights•Propose Graph Differential Equation to model the continuity of users’ interest.•Combine sequence- and graph-based models to obtain a time-serial graph.•Design Siamese learning-based strategy to alleviate the bias on negative samples.