Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation

arXiv 2503.04162 ↗First posted 6 Mar 2025cs.IR cs.AIcited by 6

On the map: Retrieval-augmented generation → RAG for recommendation

Abstract (arXiv)

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt user preference patterns or depend on sparse collaborative data that generates unreliable contrastive pairs. Furthermore, existing approaches typically require predefined selection rules that impose strong assumptions, limiting the model's ability to autonomously learn optimal contrastive pairs. To address these limitations, we propose a novel approach named Semantic Retrieval Augmented Contrastive Learning (SRA-CL). SRA-CL leverages the semantic understanding and reasoning capabilities of LLMs to generate expressive embeddings that capture both user preferences and item characteristics. These semantic embeddings enable the construction of candidate pools for inter-user and intra-user contrastive learning through semantic-based retrieval. To further enhance the quality of the contrastive samples, we introduce a learnable sample synthesizer that optimizes the contrastive sample generation process during model training. SRA-CL adopts a plug-and-play design, enabling seamless integration with existing sequential recommendation architectures. Extensive experiments on four public datasets demonstrate the effectiveness and model-agnostic nature of our approach.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation. Builds on 48 of its 59 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

48 of 59 references.

References · 48

2017Attention Is All You Needcited by 59,932
2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
2017Graph Attention Networkscited by 8,854
2020Exploring Simple Siamese Representation Learningcited by 2,853
2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
2018Self-Attentive Sequential Recommendationcited by 1,169
2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
2015Session-based Recommendations with Recurrent Neural Networkscited by 685
2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 473
2023A Survey on Large Language Models for Recommendationcited by 378

36 more

2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
2020Self-supervised Graph Learning for Recommendationcited by 305
2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 188
2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 171
2017Recurrent Neural Networks with Top-k Gains for Session-based Recommendationscited by 165
2023Representation Learning with Large Language Models for Recommendationcited by 155
2016Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendationcited by 152
2021Contrastive Learning for Representation Degeneration Problem in Sequential Recommendationcited by 121
2022Self-Supervised Learning for Recommender Systems: A Surveycited by 95
2022Intent Contrastive Learning for Sequential Recommendationcited by 90
2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73
2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 72
2021Dynamic Graph Neural Networks for Sequential Recommendationcited by 57
2021Contrastive Self-supervised Sequential Recommendation with Robust Augmentationcited by 56
2023LLaRA: Large Language-Recommendation Assistantcited by 56
2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
2024LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendationcited by 47
2023DiffKG: Knowledge Graph Diffusion Model for Recommendationcited by 41
2023Debiased Contrastive Learning for Sequential Recommendationcited by 38
2024Harnessing Large Language Models for Text-Rich Sequential Recommendationcited by 38
2023Automated Self-Supervised Learning for Recommendationcited by 37
2024Can Small Language Models be Good Reasoners for Sequential Recommendation?cited by 25
2024CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendationcited by 23
2022Multi-Behavior Sequential Recommendation with Temporal Graph Transformercited by 20
2024Sequential Recommendation with Latent Relations based on Large Language Modelcited by 17
2022Equivariant Contrastive Learning for Sequential Recommendationcited by 13
2022Adaptive Low-Precision Training for Embeddings in Click-Through Rate Predictioncited by 11
2024RecDCL: Dual Contrastive Learning for Recommendationcited by 11
2023Meta-optimized Contrastive Learning for Sequential Recommendationcited by 10
2024Improving Sequential Recommendations with LLMscited by 10
2024Comprehending Knowledge Graphs with Large Language Models for Recommender Systemscited by 9
2023Intent Contrastive Learning with Cross Subsequences for Sequential Recommendationcited by 8
2024FineRec:Exploring Fine-grained Sequential Recommendationcited by 8
2024Mixed-Precision Embeddings for Large-Scale Recommendation Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

2025DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendationscited by 0
2026SLSREC: Self-Supervised Contrastive Learning for Adaptive Fusion of Long- and Short-Term User Interestscited by 0
2026Distributionally Robust Set Representation Learning Under Inference-Time Element Corruptioncited by 0
2026MEMOIR: Temporal Behavioral Memory for Recommendation Across the Preference-Drift Spectrumcited by 0
2026P3Rec: Distilling Prior--Posterior Preference Reasoning for LLM-based Recommendationcited by 0
2026Cross-Country Code-Mixing for Generative Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way