arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16375cs.IRcs.CLcs.LG
收藏

可变长度语义ID用于推荐系统

Variable-Length Semantic IDs for Recommender Systems

HSE University（俄罗斯莫斯科高等经济大学）

Kirill Khrylchenko

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出可变长度语义ID用于推荐系统，通过离散变分自编码器学习自适应长度的物品表示，解决固定长度语义ID的不足。

摘要：

生成模型在推荐系统中越来越被使用，既用于建模用户行为作为事件序列，也用于将大语言模型整合到推荐流程中。在这一设置中，一个关键挑战是物品空间的极大规模基数，这使得训练生成模型变得困难，并在自然语言和物品标识符之间引入了词汇差距。语义标识符（语义ID），将物品表示为低基数令牌序列，最近出现作为解决这个问题的有效方法。然而，现有方法生成固定长度的语义标识符，对所有物品分配相同的描述长度。这效率低下，与自然语言不匹配，并忽略了现实世界目录中高度偏斜的频率结构，其中流行物品和罕见长尾物品表现出根本不同的信息需求。同时，新兴的通信文献研究了代理如何发展离散通信协议，通常产生可变长度的消息，其中频繁的概念接收较短的描述。尽管概念相似，这些想法尚未在推荐系统中系统地采用。在本工作中，我们通过引入可变长度语义标识符来连接推荐系统和新兴通信，提出了一种离散变分自编码器，使用Gumbel-Softmax重参数化，在原理上概率框架下学习具有自适应长度的物品表示，避免了基于REINFORCE的训练的不稳定性以及先前语义ID方法的固定长度限制。

英文摘要：

Generative models are increasingly used in recommender systems, both for modeling user behavior as event sequences and for integrating large language models into recommendation pipelines. A key challenge in this setting is the extremely large cardinality of item spaces, which makes training generative models difficult and introduces a vocabulary gap between natural language and item identifiers. Semantic identifiers (semantic IDs), which represent items as sequences of low-cardinality tokens, have recently emerged as an effective solution to this problem. However, existing approaches generate semantic identifiers of fixed length, assigning the same description length to all items. This is inefficient, misaligned with natural language, and ignores the highly skewed frequency structure of real-world catalogs, where popular items and rare long-tail items exhibit fundamentally different information requirements. In parallel, the emergent communication literature studies how agents develop discrete communication protocols, often producing variable-length messages in which frequent concepts receive shorter descriptions. Despite the conceptual similarity, these ideas have not been systematically adopted in recommender systems. In this work, we bridge recommender systems and emergent communication by introducing variable-length semantic identifiers for recommendation. We propose a discrete variational autoencoder with Gumbel-Softmax reparameterization that learns item representations of adaptive length under a principled probabilistic framework, avoiding the instability of REINFORCE-based training and the fixed-length constraints of prior semantic ID methods.

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。

↑