Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation

• URL: http://arxiv.org/abs/2511.12922v1
• Date: Mon, 17 Nov 2025 03:18:04 GMT
• Title: Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation
• Authors: Yu Hou, Won-Yong Shin,
• Abstract summary: UniTok is a Unified item Tokenization framework that integrates our mixture-of-experts (MoE) architecture with a series of codebooks.<n>Items from different domains are first projected into a unified latent space through a shared encoder.<n>They are then routed to domain-specific experts to capture the unique semantics, while a shared expert, which is always active, encodes common knowledge transferable across domains.
• Score: 17.136684625966073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM)-based recommender systems have achieved high-quality performance by bridging the discrepancy between the item space and the language space through item tokenization. However, existing item tokenization methods typically require training separate models for each item domain, limiting generalization. Moreover, the diverse distributions and semantics across item domains make it difficult to construct a unified tokenization that preserves domain-specific information. To address these challenges, we propose UniTok, a Unified item Tokenization framework that integrates our own mixture-of-experts (MoE) architecture with a series of codebooks to convert items into discrete tokens, enabling scalable tokenization while preserving semantic information across multiple item domains. Specifically, items from different domains are first projected into a unified latent space through a shared encoder. They are then routed to domain-specific experts to capture the unique semantics, while a shared expert, which is always active, encodes common knowledge transferable across domains. Additionally, to mitigate semantic imbalance across domains, we present a mutual information calibration mechanism, which guides the model towards retaining similar levels of semantic information for each domain. Comprehensive experiments on wide-ranging real-world datasets demonstrate that the proposed UniTok framework is (a) highly effective: achieving up to 51.89% improvements over strong benchmarks, (b) theoretically sound: showing the analytical validity of our architectural design and optimization; and (c) highly generalizable: demonstrating robust performance across diverse domains without requiring per-domain retraining, a capability not supported by existing baselines.

Related papers

• RecGPT: A Foundation Model for Sequential Recommendation [16.464972558861497]
  We develop a foundation model for sequential recommendation that achieves genuine zero-shot generalization capabilities.<n>Our approach departs from existing ID-based methods by deriving item representations exclusively from textual features.<n>We introduce unified item tokenization with Finite Scalar Quantization that transforms heterogeneous textual descriptions into standardized discrete tokens.
  arXiv  Detail & Related papers  (2025-06-06T17:53:02Z)
• Universal Item Tokenization for Transferable Generative Recommendation [89.42584009980676]
  We propose UTGRec, a universal item tokenization approach for transferable Generative Recommendation.<n>By devising tree-structured codebooks, we discretize content representations into corresponding codes for item tokenization.<n>For raw content reconstruction, we employ dual lightweight decoders to reconstruct item text and images from discrete representations.<n>For collaborative knowledge integration, we assume that co-occurring items are similar and integrate collaborative signals through co-occurrence alignment and reconstruction.
  arXiv  Detail & Related papers  (2025-04-06T08:07:49Z)
• Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation [55.99632509895994]
  We introduce LAMIA, a novel approach for multi-aspect semantic tokenization.<n>Unlike RQ-VAE, which uses a single embedding, LAMIA learns an item palette''--a collection of independent and semantically parallel embeddings.<n>Our results demonstrate significant improvements in recommendation accuracy over existing methods.
  arXiv  Detail & Related papers  (2024-09-11T13:49:48Z)
• Unified Language-driven Zero-shot Domain Adaptation [55.64088594551629]
  Unified Language-driven Zero-shot Domain Adaptation (ULDA) is a novel task setting. It enables a single model to adapt to diverse target domains without explicit domain-ID knowledge.
  arXiv  Detail & Related papers  (2024-04-10T16:44:11Z)
• Cross-domain Recommender Systems via Multimodal Domain Adaptation [2.306402684958048]
  Collaborative Filtering (CF) has emerged as one of the most prominent implementation strategies for building recommender systems.<n>Cross-domain CF alleviates the problem of data sparsity by finding a common set of entities (users or items) across the domains.<n>This paper introduces a domain adaptation technique to align the embeddings of entities across domains.
  arXiv  Detail & Related papers  (2023-06-24T07:27:43Z)
• Multi-Domain Learning From Insufficient Annotations [26.83058974786833]
  Multi-domain learning refers to simultaneously constructing a model or a set of models on datasets collected from different domains. In this paper, we introduce a novel method called multi-domain contrastive learning to alleviate the impact of insufficient annotations. Experimental results across five datasets demonstrate that MDCL brings noticeable improvement over various SP models.
  arXiv  Detail & Related papers  (2023-05-04T11:50:19Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains [108.11746235308046]
  We propose a novel approach that learns domain-agnostic structured latent embeddings by projecting images from different domains. Our experiments on the challenging DomainNet and DomainNet-LS benchmarks show the superiority of our approach over existing methods.
  arXiv  Detail & Related papers  (2021-07-12T17:57:46Z)
• Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN [117.80737222754306]
  We present a novel universal object detector called Universal-RCNN. We first generate a global semantic pool by integrating all high-level semantic representation of all the categories. An Intra-Domain Reasoning Module learns and propagates the sparse graph representation within one dataset guided by a spatial-aware GCN.
  arXiv  Detail & Related papers  (2020-02-18T07:57:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.