UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization

• URL: http://arxiv.org/abs/2601.17438v1
• Date: Sat, 24 Jan 2026 12:20:29 GMT
• Title: UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization
• Authors: Jialei Li, Yang Zhang, Yimeng Bai, Shuai Zhu, Ziqi Xue, Xiaoyan Zhao, Dingxian Wang, Frank Yang, Andrew Rabinovich, Xiangnan He,
• Abstract summary: We propose a unified generative recommendation framework, UniGRec.<n>UniGRec addresses training-inference discrepancy, item identifier collapse from codeword usage, and collaborative signal deficiency.<n>Experiments on real-world datasets demonstrate that UniGRec consistently outperforms state-of-the-art baseline methods.
• Score: 20.538589808672963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative recommendation has recently emerged as a transformative paradigm that directly generates target items, surpassing traditional cascaded approaches. It typically involves two components: a tokenizer that learns item identifiers and a recommender trained on them. Existing methods often decouple tokenization from recommendation or rely on asynchronous alternating optimization, limiting full end-to-end alignment. To address this, we unify the tokenizer and recommender under the ultimate recommendation objective via differentiable soft item identifiers, enabling joint end-to-end training. However, this introduces three challenges: training-inference discrepancy due to soft-to-hard mismatch, item identifier collapse from codeword usage imbalance, and collaborative signal deficiency due to an overemphasis on fine-grained token-level semantics. To tackle these challenges, we propose UniGRec, a unified generative recommendation framework that addresses them from three perspectives. UniGRec employs Annealed Inference Alignment during tokenization to smoothly bridge soft training and hard inference, a Codeword Uniformity Regularization to prevent identifier collapse and encourage codebook diversity, and a Dual Collaborative Distillation mechanism that distills collaborative priors from a lightweight teacher model to jointly guide both the tokenizer and the recommender. Extensive experiments on real-world datasets demonstrate that UniGRec consistently outperforms state-of-the-art baseline methods. Our codes are available at https://github.com/Jialei-03/UniGRec.

Related papers

• Differentiable Semantic ID for Generative Recommendation [65.83703273297492]
  Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content.<n>In practice, SIDs are typically optimized only for content reconstruction rather than recommendation accuracy.<n>A natural approach is to make semantic indexing differentiable so that recommendation gradients can directly influence SID learning.<n>We propose DIGER, a first step toward effective differentiable semantic IDs for generative recommendation.
  arXiv  Detail & Related papers  (2026-01-27T15:34:11Z)
• Token-Weighted Multi-Target Learning for Generative Recommenders with Curriculum Learning [8.152671524863083]
  We propose two complementary information-gain-based token-weighting strategies tailored to generative recommendation with semantic IDs.<n>We introduce a multi-target learning framework with curriculum learning that jointly optimize the two token-weighted objectives alongside standard likelihood.
  arXiv  Detail & Related papers  (2026-01-25T11:01:14Z)
• Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation [42.09028908758132]
  Generative recommendation is emerging as a transformative paradigm by directly generating recommended items, rather than relying on matching.<n>Existing approaches treat the tokenizer to derive suitable item identifiers and the recommender based on those identifiers separately.<n>We propose BLOGER, a Bi-Level Optimization for GEnerative Recommendation framework, which explicitly models the interdependence between the tokenizer and the recommender.
  arXiv  Detail & Related papers  (2025-10-24T08:25:56Z)
• Closing the Performance Gap in Generative Recommenders with Collaborative Tokenization and Efficient Modeling [10.757287948514604]
  We introduce a contrastive tokenization method that integrates collaborative information directly into the learned item representations.<n>We also propose MARIUS, a lightweight, audio-inspired generative model that decouples timeline modeling from item decoding.
  arXiv  Detail & Related papers  (2025-08-12T17:06:55Z)
• 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)
• Pre-training Generative Recommender with Multi-Identifier Item Tokenization [78.87007819266957]
  We propose MTGRec to augment token sequence data for Generative Recommender pre-training.<n>Our approach involves two key innovations: multi-identifier item tokenization and curriculum recommender pre-training.<n>Extensive experiments on three public benchmark datasets demonstrate that MTGRec significantly outperforms both traditional and generative recommendation baselines.
  arXiv  Detail & Related papers  (2025-04-06T08:03:03Z)
• Generative Recommender with End-to-End Learnable Item Tokenization [51.82768744368208]
  We introduce ETEGRec, a novel End-To-End Generative Recommender that unifies item tokenization and generative recommendation into a cohesive framework.<n>ETEGRec consists of an item tokenizer and a generative recommender built on a dual encoder-decoder architecture.<n>We develop an alternating optimization technique to ensure stable and efficient end-to-end training of the entire framework.
  arXiv  Detail & Related papers  (2024-09-09T12:11:53Z)
• 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)
• Learnable Item Tokenization for Generative Recommendation [113.80559032128065]
  We propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity.<n> LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias.
  arXiv  Detail & Related papers  (2024-05-12T15:49:38Z)

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.