Skip to content
Book Open access

Not All Branches Are Equal: Adaptive Semantic ID Construction for Generative Recommendation

Sep 2026 · Proceedings of the 20th ACM Conference on Recommender Systems · pp. 390-399 · 0 citations · 55 references

TL;DR

Adaptive Silhouette Tree (AST) is proposed, a top-down divisive clustering method that constructs semantic IDs as paths within a tree structure that significantly outperforms strong baselines on Amazon Review datasets of varying sizes and domains.

Abstract

Generative recommendation models represent items as sequences of discrete tokens known as semantic IDs. Existing approaches derive these identifiers using residual or hierarchical vector quantization, assuming that tokens carry independent semantic meaning across quantization levels. Revisiting this assumption, we argue that semantic IDs should behave as hierarchical paths where each token’s meaning is conditioned on its prefix. This highlights a mismatch between conventional fixed-codebook quantization and the hierarchical structure implicitly learned by generative recommenders. Motivated by this insight, we propose Adaptive Silhouette Tree (AST), a top-down divisive clustering method that constructs semantic IDs as paths within a tree structure. Unlike prior methods with fixed branching factors, AST dynamically determines the number of branches at each node by maximizing the silhouette coefficient, enabling finer partitions in dense regions and compact groupings in homogeneous ones. We further introduce constrained variants that enforce minimum probability mass during splitting to improve supervision for long-tail items. Extensive experiments on five Amazon Review datasets of varying sizes and domains show that AST significantly outperforms strong baselines. These results demonstrate that aligning semantic ID construction with the inherent hierarchical structure of generative recommenders leads to more effective recommendations.

Read PDF

Similar papers

Book Open access Nov 2026

Preference-Aligned Semantic IDs for Generative Recommendation

Semantic IDs (SIDs) are becoming a practical interface for generative recommendation. Existing pipelines usually build them by quantizing frozen content embeddings, implicitly assuming that content similarity is the right geometry for recommendation. This assumption is often too strong: items that look similar in conte...

Valentin Tsaruk, Danil Gusak, Rostislav Korst et al. · 0 citations
Book Open access Nov 2026

Personalized Context-Conditioned Tokenization for Generative Recommendation

Generative recommendation (GR) represents user actions as sequences of discrete tokens (often referred to as semantic IDs) and predict future interactions through autoregressive generation. This paradigm offers advantages such as compact representations, scalability, and the potential to unify retrieval and ranking. Ho...

Qi-Yong Zhong, Jia-Jie Su, Yun-Shan Ma et al. · 0 citations
#artificial intelligence Preprint Sep 2026

FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation

FineSID is a unified quantization framework that moves beyond Top-1 assignment by enabling fine-grained gradient propagation across the entire codebook, effectively alleviating SID collisions and stabilizing training in large, high-dimensional codebooks.

Song-Li Wu, Wei-Nan Gan, Zhao-Cheng Du et al. · 2 citations
Preprint Oct 2026

Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment

Semantic ID-based generative recommendation represents each item as a sequence of discrete tokens, enabling structured modeling of item semantics. A critical challenge is constructing semantic IDs that are both semantically expressive and computationally efficient. While recent approaches favor complex learned quantiza...

Yu-Qing Liu, Hui-Yuan Chen, Yi-Bo Wang et al. · 0 citations
Book Open access Sep 2026

CoSID: Concept-Conditioned Semantic-ID Decoding for Efficient Generative Recommendation

Generative recommenders retrieve items by autoregressively decoding semantic IDs (SIDs). The standard autoregressive SID interface (SID-AR) represents each history item with K code tokens, expanding a T-item history to TK tokens, while trie-constrained beam search repeatedly re-enters the full backbone during generatio...

Danil Gusak, A. Volodkevich, Evgeny Frolov · 3 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.