IeMTLF: Interaction-enhanced Multi-Task Learning Framework for next location prediction

Yahui Wang, Hongchang Chen, Shuxin Liu, Kai Wang, Xing Li, Yuxiang Hu

Abstract: Highlights•A novel multi-task learning framework for predicting locations and their semantics.•Explicit feature interaction to improve location prediction performance.•Feature interactions providing more complementary features are more beneficial.•Specific semantics for precise prediction and abstract semantics for fuzzy prediction.