paper-with-me

Papers

CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendation

2024-04-23 · Jieming Zhu, mengqun Jin, Qijiong Liu, Zexuan Qiu, Zhenhua Dong, Xiu Li

Embedding-based retrieval serves as a dominant approach to candidate item matching for industrial recommender systems. With the success of generative AI, generative retrieval has recently emerged as a new retrieval paradigm for recommendation, which casts item retrieval as a generation problem. Its model consists of two stages: semantic tokenization and autoregressive generation. The first stage involves item tokenization that constructs discrete semantic tokens to index items, while the second stage autoregressively generates semantic tokens of candidate items. Therefore, semantic tokenization serves as a crucial preliminary step for training generative recommendation models. Existing research usually employs a vector quantizier with reconstruction loss (e.g., RQ-VAE) to obtain semantic tokens of items, but this method fails to capture the essential neighborhood relationships that are vital for effective item modeling in recommender systems. In this paper, we propose a contrastive quantization-based semantic tokenization approach, named CoST, which harnesses both item relationships and semantic information to learn semantic tokens. Our experimental results highlight the significant impact of semantic tokenization on generative recommendation performance, with CoST achieving up to a 43% improvement in Recall@5 and 44% improvement in NDCG@5 on the MIND dataset over previous baselines.

📄 PDF Abstract BibTeX arXiv:2404.14774

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderLanguage ModellingQuantizationRecommendation SystemsRetrievalSequential Recommendation

Similar Papers 제목 키워드 기반

A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation

2025-06-20 · Penglong Zhai, Yifang Yuan, Fanyi Di, Jie Li 외

Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes …

Contrastive LearningDescriptiveQuantizationRecommendation Systems+1

Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs

2026-02-02 · Yu Liang, Zhongjin Zhang, Yuxuan Zhu, Kerui Zhang 외 arxiv

Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation mode…

Representation Learning

PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation

2026-01-23 · Dengzhao Fang, Jingtong Gao, Yu Li, Xiangyu Zhao 외 arxiv

Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-bas…

Sequential Recommendation

STORE: Streamlining Semantic Tokenization and Generative Recommendation with A Single LLM

2024-09-11 · Qijiong Liu, Jieming Zhu, Lu Fan, Zhou Zhao 외

Traditional recommendation models often rely on unique item identifiers (IDs) to distinguish between items, which can hinder their ability to effectively leverage item content information and generalize to long-tail or c…

Language ModellingLarge Language ModelQuantization

Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization

2026-03-17 · Wenhao Zhao, Qiran Zou, Zhouhan Lin, Dianbo Liu arxiv

Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discr…