BIPCL: Bilateral Intent-Enhanced Sequential Recommendation via Embedding Perturbation Contrastive Learning

TL;DR

BIPCL introduces a novel contrastive learning framework that enhances sequential recommendation by integrating multi-intent signals and embedding perturbations, leading to improved robustness and performance.

Contribution

It presents an end-to-end bilateral intent-enhanced contrastive learning method that explicitly models shared intent signals and injects perturbations into embeddings for better recommendations.

Findings

BIPCL outperforms state-of-the-art baselines on benchmark datasets.

The bilateral intent mechanism effectively captures collective intent semantics.

Embedding perturbations improve model robustness under sparse supervision.

Abstract

Accurately modeling users' evolving preferences from sequential interactions remains a central challenge in recommender systems. Recent studies emphasize the importance of capturing multiple latent intents underlying user behaviors. However, existing methods often fail to effectively exploit collective intent signals shared across users and items, leading to information isolation and limited robustness. Meanwhile, current contrastive learning approaches struggle to construct views that are both semantically consistent and sufficiently discriminative. In this work, we propose BIPCL, an end-to-end Bilateral Intent-enhanced, Embedding Perturbation-based Contrastive Learning framework. BIPCL explicitly integrates multi-intent signals into both item and sequence representations via a bilateral intent-enhancement mechanism. Specifically, shared intent prototypes on the user and item sides capture collective intent semantics distilled from behaviorally similar entities, which are subsequently integrated into representation learning. This design alleviates information isolation and improves robustness under sparse supervision. To construct effective contrastive views without disrupting temporal or structural dependencies, BIPCL injects bounded, direction-aware perturbations directly into structural item embeddings. On this basis, BIPCL further enforces multi-level contrastive alignment across interaction- and intent-level representations. Extensive experiments on benchmark datasets demonstrate that BIPCL consistently outperforms state-of-the-art baselines, with ablation studies confirming the contribution of each component.