arXiv Machine Learning
PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Aug 25
PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization
Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a co...
arXiv AI
Sep 30
FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation
FineSID introduces a new quantization framework for semantic identifier learning in generative recommendation systems. By replacing the traditional Top‑1 hard assignment with a soft, differentiable approach, it distributes gradient updates across all codewords, leading to balanced codebook optimization and reduced identifier collisions. Experiments on public benchmarks show that FineSID improves codebook utilization and recommendation accuracy without relying on complex initialization strategies.
arXiv Machine Learning
Aug 24
From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation
The paper proposes replacing a static multi‑level small semantic codebook with a dynamic single‑level large semantic codebook for generative recommendation. It introduces an exposure‑aware update mechanism and an offline evaluation framework, achieving significant improvements in recall, NDCG, decoding efficiency, and online consumption metrics on public datasets and production traffic.
arXiv Machine Learning
Sep 22
Guiding the coarse levels of semantic IDs makes the fine levels learnable
arXiv:2609.22227v1 Announce Type: cross Abstract: Generative retrieval represents each item by a short Semantic ID and casts recommendation as autoregressive generation of that sequence. Because the...
arXiv AI
1d ago
Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation
The paper introduces two continuous-query paradigms—CQG‑Single and CQG‑AR—to replace the traditional finite-beam, discrete Semantic ID (SID) decoding used in generative recommendation systems. By removing the SID vocabulary and beam expansion, these methods allow every encoded item to be directly scored via dense or approximate-nearest-neighbor retrieval, thereby eliminating the reachability constraints of finite-beam decoding. Experiments show that CQG‑Single outperforms a TIGER-style baseline across all runs while using fewer parameters, and CQG‑AR performs comparably or better on several datasets, suggesting that decoupling output representation, autoregressive modeling, and retrieval budget can improve generative recommendation evaluation.
arXiv AI
Aug 3
Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding
arXiv:2607. 28659v1 Announce Type: new Abstract: Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains.