Analyzing and Mitigating Repetitions in Trip Recommendation

TL;DR

This paper investigates the causes of repetitive outputs in trip recommendation models and proposes AR-Trip, a cycle-aware predictor that reduces repetition and improves recommendation precision.

Contribution

The paper identifies the link between model strategies and repetition, and introduces AR-Trip with mechanisms to effectively mitigate repetition in trip recommendations.

Findings

AR-Trip reduces repetition in trip recommendations.

AR-Trip improves recommendation precision.

Experimental results on four datasets validate effectiveness.

Abstract

Trip recommendation has emerged as a highly sought-after service over the past decade. Although current studies significantly understand human intention consistency, they struggle with undesired repetitive outcomes that need resolution. We make two pivotal discoveries using statistical analyses and experimental designs: (1) The occurrence of repetitions is intricately linked to the models and decoding strategies. (2) During training and decoding, adding perturbations to logits can reduce repetition. Motivated by these observations, we introduce AR-Trip (Anti Repetition for Trip Recommendation), which incorporates a cycle-aware predictor comprising three mechanisms to avoid duplicate Points-of-Interest (POIs) and demonstrates their effectiveness in alleviating repetition. Experiments on four public datasets illustrate that AR-Trip successfully mitigates repetition issues while enhancing precision.