S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

2020/08/18 by Kun Zhou, Hui Wang, Wayne Xin Zhao +5 · 9 citations
Computer Science · #Advanced Graph Neural Networks #Artificial neural network #Context (archaeology) #Context model #Deep learning #Information loss #Maximization #Mutual information #Recommender Systems and Techniques #Sequence (biology) #Topic Modeling #cs.IR #cs.LG

paper · pdf · doi:10.1145/3340531.3411954

Accepted as CIKM2020 long paper

arxiv created 2020/08/18 · arxiv updated 2020/08/19 · openalex created_date 2020/08/24 · openalex publication_date 2020/10/19 · openalex updated_date 2026/08/06

Abstract

Recently, significant progress has been made in sequential recommendation with deep learning. Existing neural sequential recommendation models usually rely on the item prediction loss to learn model parameters or data representations. However, the model trained with this loss is prone to suffer from data sparsity problem. Since it overemphasizes the final performance, the association or fusion between context data and sequence data has not been well captured and utilized for sequential recommendation.

Cited by

• IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval
• MMHCL: Multi-Modal Hypergraph Contrastive Learning for Recommendation
• Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model
• Disentangling Long and Short-Term Interests for Recommendation
• Intent-aware Diffusion with Contrastive Learning for Sequential Recommendation
• Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation
• Improving Sequential Recommenders through Counterfactual Augmentation of System Exposure
• Filter-enhanced MLP is All You Need for Sequential Recommendation
• Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration