考虑漂移的生成推荐持续分词
Drift-Aware Continual Tokenization for Generative Recommendation
AI总结:
本文提出DACT框架,通过分词微调和分层代码重新分配,解决生成推荐中持续漂移带来的分词冲突问题,提升推荐质量并减少对已有知识的干扰。
摘要:
生成推荐通常采用两阶段流程,其中可学习的分词器将项目映射到离散的令牌序列(即标识符),然后基于这些标识符的自回归生成推荐模型(GRM)进行预测。最近的分词器进一步结合了协同信号,使得具有相似用户行为模式的项目接收相似代码,显著提高了推荐质量。然而,现实环境持续演变:新项目导致标识符冲突和位移,而新交互会诱导现有项目中的协同漂移(例如,改变共现模式和流行度)。完全重新训练分词器和GRM通常成本高昂,而简单微调分词器会改变大多数现有项目的令牌序列,破坏GRM学习的令牌-嵌入对齐。为了平衡分词的可塑性和稳定性,我们提出DACT,一种考虑漂移的持续分词框架,包含两个阶段:(i)分词微调,辅以联合训练的协同漂移识别模块(CDIM),输出项目级漂移置信度,并为漂移和静止项目实现差异化优化;(ii)使用放松到严格策略的分层代码重新分配,更新令牌序列的同时限制不必要的更改。在三个真实世界数据集上使用两种代表性GRM的实验表明,DACT在持续漂移环境下比基线方法表现更好,证明了有效适应协同演变并减少对已有知识的干扰。我们的实现可在https://github.com/HomesAmaranta/DACT上公开获取以供复现。
英文摘要:
Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive generative recommender model (GRM) performs prediction based on these identifiers. Recent tokenizers further incorporate collaborative signals so that items with similar user-behavior patterns receive similar codes, substantially improving recommendation quality. However, real-world environments evolve continuously: new items cause identifier collision and shifts, while new interactions induce collaborative drift in existing items (e.g., changing co-occurrence patterns and popularity). Fully retraining both tokenizer and GRM is often prohibitively expensive, yet naively fine-tuning the tokenizer can alter token sequences for the majority of existing items, undermining the GRM's learned token-embedding alignment. To balance plasticity and stability for collaborative tokenizers, we propose DACT, a Drift-Aware Continual Tokenization framework with two stages: (i) tokenizer fine-tuning, augmented with a jointly trained Collaborative Drift Identification Module (CDIM) that outputs item-level drift confidence and enables differentiated optimization for drifting and stationary items; and (ii) hierarchical code reassignment using a relaxed-to-strict strategy to update token sequences while limiting unnecessary changes. Experiments on three real-world datasets with two representative GRMs show that DACT consistently achieves better performance than baselines, demonstrating effective adaptation to collaborative evolution with reduced disruption to prior knowledge. Our implementation is publicly available at https://github.com/HomesAmaranta/DACT for reproducibility.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。