Contrastive Self-supervised Sequential Recommendation with Robust Augmentation

Abstract

Sequential Recommendationdescribes a set of techniques to model dynamic user behavior in order to predict future interactions in sequential user data. At their core, such approaches model transition probabilities between items in a sequence, whether through Markov chains, recurrent networks, or more recently, Transformers. However both old and new issues remain, including data-sparsity and noisy data; such issues can impair the performance, especially in complex, parameter-hungry models. In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues. Contrastive SSL constructs augmentations from unlabelled instances, where agreements among positive pairs are maximized. It is challenging to devise a contrastive SSL framework for a sequential recommendation, due to its discrete nature, correlations among items, and skewness of length distributions. To this end, we propose a novel framework, Contrastive Self-supervised Learning for sequential Recommendation (CoSeRec). We introduce two informative augmentation operators leveraging item correlations to create high-quality views for contrastive learning. Experimental results on three real-world datasets demonstrate the effectiveness of the proposed method on improving model performance and the robustness against sparse and noisy data. Our implementation is available online at \url{https://github.com/YChen1993/CoSeRec}

arXiv commentUnder-review. Work done during Zhiwei's intern at Salesforce. Inc

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Graph Contrastive Learning with Adaptive Augmentation
• Session-based Recommendations with Recurrent Neural Networks
• Denoising Implicit Feedback for Recommendation
• CLEAR: Contrastive Learning for Sentence Representation
• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• What Should Not Be Contrastive in Contrastive Learning
• Self-supervised Learning for Large-scale Item Recommendations
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems
• Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation

Cited by in corpus (10)

• Knowledge Graph Contrastive Learning for Recommendation
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• Graph Masked Autoencoder for Sequential Recommendation
• Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?
• On the Effectiveness of Unlearning in Session-Based Recommendation
• Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
• Modeling Dynamic Attributes for Next Basket Recommendation
• A Survey of Latent Factor Models in Recommender Systems
• RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation
• Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning