Learnable Sequence Augmenter for Triplet Contrastive Learning in Sequential Recommendation

2025-03-26

AI Summary

Existing contrastive learning–based sequential recommendation methods heavily rely on random data augmentation, which often disrupts genuine item correlations, leading to distorted positive samples and biased representation learning. To address this, we propose LearnAug: (1) a novel learnable sequence augmenter that dynamically prunes noisy items and reconstructs salient ones via self-supervised learning, generating semantically consistent, high-quality positive samples; and (2) a ranking-aware triplet contrastive loss that provides fine-grained discriminative signals, mitigating negative sampling bias inherent in conventional contrastive losses. Extensive experiments on three real-world datasets demonstrate that LearnAug significantly outperforms state-of-the-art methods—including CL4SRec—validating the effectiveness and robustness of learnable augmentation and structured contrastive objectives for sequential representation learning.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning Preferences or Rankings
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Most existing contrastive learning-based sequential recommendation (SR) methods rely on random operations (e.g., crop, reorder, and substitute) to generate augmented sequences. These methods often struggle to create positive sample pairs that closely resemble the representations of the raw sequences, potentially disrupting item correlations by deleting key items or introducing noisy iterac, which misguides the contrastive learning process. To address this limitation, we propose Learnable sequence Augmentor for triplet Contrastive Learning in sequential Recommendation (LACLRec). Specifically, the self-supervised learning-based augmenter can automatically delete noisy items from sequences and insert new items that better capture item transition patterns, generating a higher-quality augmented sequence. Subsequently, we randomly generate another augmented sequence and design a ranking-based triplet contrastive loss to differentiate the similarities between the raw sequence, the augmented sequence from augmenter, and the randomly augmented sequence, providing more fine-grained contrastive signals. Extensive experiments on three real-world datasets demonstrate that both the sequence augmenter and the triplet contrast contribute to improving recommendation accuracy. LACLRec significantly outperforms the baseline model CL4SRec, and demonstrates superior performance compared to several state-of-the-art sequential recommendation algorithms.

Problem

• Improving sequence augmentation in contrastive learning for recommendations
• Reducing noise in augmented sequences for better item correlations
• Enhancing recommendation accuracy with triplet contrastive learning

Innovation

• Learnable augmenter deletes noisy items
• Insert items capturing transition patterns
• Ranking-based triplet contrastive loss