Denoising Long- and Short-term Interests for Sequential Recommendation

TL;DR

This paper introduces LSIDN, a novel neural network that effectively denoises and models both long-term and short-term user interests for improved sequential recommendation, addressing noise issues across different time scales.

Contribution

The paper proposes a new model with tailored denoising strategies for long- and short-term interests, enhancing robustness and recommendation accuracy.

Findings

Outperforms state-of-the-art models on two datasets

Achieves significant robustness against behavioral noise

Effectively models interests across different time scales

Abstract

User interests can be viewed over different time scales, mainly including stable long-term preferences and changing short-term intentions, and their combination facilitates the comprehensive sequential recommendation. However, existing work that focuses on different time scales of user modeling has ignored the negative effects of different time-scale noise, which hinders capturing actual user interests and cannot be resolved by conventional sequential denoising methods. In this paper, we propose a Long- and Short-term Interest Denoising Network (LSIDN), which employs different encoders and tailored denoising strategies to extract long- and short-term interests, respectively, achieving both comprehensive and robust user modeling. Specifically, we employ a session-level interest extraction and evolution strategy to avoid introducing inter-session behavioral noise into long-term interest modeling; we also adopt contrastive learning equipped with a homogeneous exchanging augmentation to alleviate the impact of unintentional behavioral noise on short-term interest modeling. Results of experiments on two public datasets show that LSIDN consistently outperforms state-of-the-art models and achieves significant robustness.