SyncAI.news, a Varaisys broadcasting
FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation
SW

Song-Li Wu, Weinan Gan, Zhaocheng Du, Xianquan Wang, Jingyi Wang

· 1 min read

ResearcharXiv cs.AI

FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation

arXiv:2609.36670v1 Announce Type: new Abstract: A critical prerequisite of generative recommendation is designing semantic identifiers (SIDs) that are both scalable to large item sets and efficiently learnable. Existing SID learning methods fundamentally rely on Top-1 hard assignment during vector quantization. While heuristic strategies -- such as clustering-based initialization or forced post-hoc collision resolution -- can artificially inflate codebook coverage, they often disrupt end-to-end semantic alignment and fail to address the underlying optimization bottleneck: sparse gradient propagation. In standard Top-1 assignment, gradients concentrate on a narrow subset of frequently selected codewords, leaving the majority inherently under-trained and causing severe SID collisions. To overcome this limitation natively without relying on complex initialization priors, we propose FineSID, a unified quantization framework that moves beyond Top-1 assignment by enabling fine-grained gradient propagation across the entire codebook. Instead of updating only a single selected codeword, FineSID distributes learning signals to all codewords in a soft, differentiable manner. This design promotes globally balanced codebook optimization while strictly preserving semantic consistency, effectively alleviating SID collisions and stabilizing training in large, high-dimensional codebooks. Extensive experiments on multiple public benchmarks demonstrate that FineSID is robust to initialization configurations and consistently improves both codebook utilization and recommendation accuracy. Our work provides a principled, initialization-agnostic solution for semantic identifier learning, advancing the practicality of generative recommendation.

Original source

This story was published by arXiv cs.AI and written by Song-Li Wu, Weinan Gan, Zhaocheng Du, Xianquan Wang, Jingyi Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News