Similarity-Guided Diffusion for Contrastive Sequential Recommendation

TL;DR

This paper introduces a similarity-guided diffusion method for contrastive sequential recommendation, improving data augmentation by preserving semantic consistency and structural information, leading to better recommendation accuracy.

Contribution

It proposes a novel augmentation technique that leverages item similarity and confidence scores to generate more meaningful training samples in contrastive learning.

Findings

Outperforms baseline models on five benchmark datasets.

Provides more discriminative positive and negative samples.

Enhances training efficiency and recommendation performance.

Abstract

In sequential recommendation systems, data augmentation and contrastive learning techniques have recently been introduced using diffusion models to achieve robust representation learning. However, most of the existing approaches use random augmentation, which risk damaging the contextual information of the original sequence. Accordingly, we propose a Similarity-Guided Diffusion for Contrastive Sequential Recommendation. Our method leverages the similarity between item embedding vectors to generate semantically consistent noise. Moreover, we utilize high confidence score in the denoising process to select our augmentation positions. This approach more effectively reflects contextual and structural information compared to augmentation at random positions. From a contrastive learning perspective, the proposed augmentation technique provides more discriminative positive and negative samples, simultaneously improving training efficiency and recommendation performance. Experimental results on five benchmark datasets show that SimDiffRec outperforms the existing baseline models.