Explanation Guided Contrastive Learning for Sequential Recommendation

TL;DR

This paper introduces EC4SRec, a novel contrastive learning framework for sequential recommendation that uses explanation-guided data augmentation to generate more semantically meaningful positive and negative sequences, leading to improved recommendation accuracy.

Contribution

The paper proposes Explanation Guided Augmentations (EGA) and EC4SRec, a contrastive learning framework that leverages explanation methods to enhance sequence augmentation for better recommendation performance.

Findings

EC4SRec outperforms state-of-the-art methods on four benchmark datasets.

EC4SRec improves different sequence encoder backbones like GRU4Rec and Caser.

The method effectively utilizes explanation-guided data augmentation to enhance sequence representations.

Abstract

Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) sequence obtained by some random augmentation (or sequence sampling) on a given anchor user sequence remains to be semantically similar (or different). When the positive and negative sequences turn out to be false positive and false negative respectively, it may lead to degraded recommendation performance. In this work, we address the above problem by proposing Explanation Guided Augmentations (EGA) and Explanation Guided Contrastive Learning for Sequential Recommendation (EC4SRec) model framework. The key idea behind EGA is to utilize explanation method(s) to determine items' importance in a user sequence and derive the positive and negative sequences accordingly. EC4SRec then combines both self-supervised and supervised contrastive learning over the positive and negative sequences generated by EGA operations to improve sequence representation learning for more accurate recommendation results. Extensive experiments on four real-world benchmark datasets demonstrate that EC4SRec outperforms the state-of-the-art sequential recommendation methods and two recent contrastive learning-based sequential recommendation methods, CL4SRec and DuoRec. Our experiments also show that EC4SRec can be easily adapted for different sequence encoder backbones (e.g., GRU4Rec and Caser), and improve their recommendation performance.