Debiased Contrastive Learning for Sequential Recommendation

Abstract

Current sequential recommender systems are proposed to tackle the dynamic user preference learning with various neural techniques, such as Transformer and Graph Neural Networks (GNNs). However, inference from the highly sparse user behavior data may hinder the representation ability of sequential pattern encoding. To address the label shortage issue, contrastive learning (CL) methods are proposed recently to perform data augmentation in two fashions: (i) randomly corrupting the sequence data (e.g. stochastic masking, reordering); (ii) aligning representations across pre-defined contrastive views. Although effective, we argue that current CL-based methods have limitations in addressing popularity bias and disentangling of user conformity and real interest. In this paper, we propose a new Debiased Contrastive learning paradigm for Recommendation (DCRec) that unifies sequential pattern encoding with global collaborative relation modeling through adaptive conformity-aware augmentation. This solution is designed to tackle the popularity bias issue in recommendation systems. Our debiased contrastive learning framework effectively captures both the patterns of item transitions within sequences and the dependencies between users across sequences. Our experiments on various real-world datasets have demonstrated that DCRec significantly outperforms state-of-the-art baselines, indicating its efficacy for recommendation. To facilitate reproducibility of our results, we make our implementation of DCRec publicly available at: https://github.com/HKUDS/DCRec.

arXiv commentThis paper is accepted by WWW'2023

References in corpus (16)

• Representation Learning with Contrastive Predictive Coding
• Session-based Recommendation with Graph Neural Networks
• Self-supervised Graph Learning for Recommendation
• Graph Contrastive Learning with Adaptive Augmentation
• Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
• S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
• Knowledge Graph Contrastive Learning for Recommendation
• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• Hypergraph Contrastive Collaborative Filtering
• Intent Contrastive Learning for Sequential Recommendation
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
• AutoDebias: Learning to Debias for Recommendation
• CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
• LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations

Cited by in corpus (12)

• Representation Learning with Large Language Models for Recommendation
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• A Survey on Popularity Bias in Recommender Systems
• Graph Transformer for Recommendation
• Learning Graph ODE for Continuous-Time Sequential Recommendation
• Graph Masked Autoencoder for Sequential Recommendation
• SSLRec: A Self-Supervised Learning Framework for Recommendation
• Diffusion-based Contrastive Learning for Sequential Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential Recommendation
• Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
• Multi-Item-Query Attention for Stable Sequential Recommendation