Joint Triplet Loss Learning for Next New POI Recommendation

TL;DR

This paper introduces a novel Joint Triplet Loss Learning (JTLL) module that enhances next new POI recommendation by effectively learning user preferences despite data sparsity, improving existing models on real-world datasets.

Contribution

The paper proposes a new JTLL module that jointly trains with existing methods to better learn unvisited POI relations, addressing data sparsity in next new POI recommendation.

Findings

JTLL improves recommendation accuracy on real-world datasets.

Joint training enhances the learning of unvisited POI relations.

Experimental results show performance gains over existing approaches.

Abstract

Sparsity of the User-POI matrix is a well established problem for next POI recommendation, which hinders effective learning of user preferences. Focusing on a more granular extension of the problem, we propose a Joint Triplet Loss Learning (JTLL) module for the Next New ($N^2$) POI recommendation task, which is more challenging. Our JTLL module first computes additional training samples from the users' historical POI visit sequence, then, a designed triplet loss function is proposed to decrease and increase distances of POI and user embeddings based on their respective relations. Next, the JTLL module is jointly trained with recent approaches to additionally learn unvisited relations for the recommendation task. Experiments conducted on two known real-world LBSN datasets show that our joint training module was able to improve the performances of recent existing works.