Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

• URL: http://arxiv.org/abs/2509.10468v1
• Date: Fri, 22 Aug 2025 18:50:38 GMT
• Title: Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
• Authors: Yifan Liu, Yaokun Liu, Zelin Li, Zhenrui Yue, Gyuseok Lee, Ruichen Yao, Yang Zhang, Dong Wang,
• Abstract summary: We propose a unified framework that preserves pretrained semantics while enhancing the adaptability of token embeddings.<n>Experiments on three real-world datasets demonstrate that DECOR consistently outperforms state-of-the-art baselines in recommendation performance.
• Score: 17.061613097917217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pretraining versus user interaction modeling during recommender training. This objective misalignment leads to two key limitations: (i) suboptimal static tokenization, where fixed token assignments fail to reflect diverse usage contexts; and (ii) discarded pretrained semantics, where pretrained knowledge - typically from language model embeddings - is overwritten during recommender training on user interactions. To address these limitations, we propose to learn DEcomposed COntextual Token Representations (DECOR), a unified framework that preserves pretrained semantics while enhancing the adaptability of token embeddings. DECOR introduces contextualized token composition to refine token embeddings based on user interaction context, and decomposed embedding fusion that integrates pretrained codebook embeddings with newly learned collaborative embeddings. Experiments on three real-world datasets demonstrate that DECOR consistently outperforms state-of-the-art baselines in recommendation performance. Our code will be made available upon publication.

Related papers

• EncodeRec: An Embedding Backbone for Recommendation Systems [4.7014546279849805]
  We present EncodeRec, an approach designed to align textual representations with recommendation objectives while learning compact, informative embeddings.<n> Experiments across core recommendation benchmarks demonstrate its effectiveness both as a backbone for sequential recommendation models and for semantic ID tokenization.<n>These results underscore the pivotal role of embedding adaptation in bridging the gap between general-purpose language models and practical recommender systems.
  arXiv  Detail & Related papers  (2026-01-15T20:15:01Z)
• AttriPrompt: Dynamic Prompt Composition Learning for CLIP [41.37140060183439]
  AttriPrompt is a novel framework that enhances and refines textual semantic representations.<n>We introduce a Self-Regularization mechanism by applying explicit regularization constraints between the prompted and non-prompted text features.<n>Experiments demonstrate AttriPrompt's superiority over state-of-the-art methods, achieving up to 7.37% improvement in the base-to-novel setting.
  arXiv  Detail & Related papers  (2025-09-07T07:07:59Z)
• EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration [63.112790050749695]
  We introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information. We validate the effectiveness of EAGER on four public benchmarks, demonstrating its superior performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-20T06:21:56Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• Dual-Alignment Pre-training for Cross-lingual Sentence Embedding [79.98111074307657]
  We propose a dual-alignment pre-training (DAP) framework for cross-lingual sentence embedding. We introduce a novel representation translation learning (RTL) task, where the model learns to use one-side contextualized token representation to reconstruct its translation counterpart. Our approach can significantly improve sentence embedding.
  arXiv  Detail & Related papers  (2023-05-16T03:53:30Z)
• RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models [12.37229805276939]
  We propose a novel pre-training method called Duplex Masked Auto-Encoder, a.k.a. DupMAE. It is designed to improve the quality semantic representation where all contextualized embeddings of the pretrained model can be leveraged.
  arXiv  Detail & Related papers  (2023-05-04T05:37:22Z)
• RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection [32.20132357830726]
  Language-Image Pre-training (LIPR) is a strategy for contrastive pre-training that leverages both entity and relation descriptions. We show the benefits of these contributions, collectively termed RLIP-ParSe, for improved zero-shot, few-shot and fine-tuning HOI detection as well as increased robustness from noisy annotations.
  arXiv  Detail & Related papers  (2022-09-05T07:50:54Z)
• COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining [59.169836983883656]
  COCO-LM is a new self-supervised learning framework that pretrains Language Models by COrrecting challenging errors and COntrasting text sequences. COCO-LM employs an auxiliary language model to mask-and-predict tokens in original text sequences. Our analyses reveal that COCO-LM's advantages come from its challenging training signals, more contextualized token representations, and regularized sequence representations.
  arXiv  Detail & Related papers  (2021-02-16T22:24:29Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)

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.