arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.12977cs.AI
收藏

超越语义ID:生成式推荐中的有限波束可达性与连续查询生成

Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation

Yu Sun, Renkai Xiang, Zuodong Xiang, Junwei Zhou, Yike Zhang, Jianxin Zhang, Zhihao Zhu, Xiaoyu Cao, Hailu Xu

AI总结:

本研究针对生成式推荐中有限波束解码的SID可达性约束,提出CQG-Single与CQG-AR两种连续查询范式,实验显示其在多数据集上性能优于或相当基线,推动相关系统的输出表示等模块解耦。

摘要:

社交媒体平台的生成式推荐(GR)通常通过有限宽度波束搜索自回归解码离散语义ID(SIDs)来检索物品。本研究探讨该输出接口如何影响保留的目标是否进入有限返回列表,同时区分全目录可评分性与经验Top-K支持度。我们引入两种连续查询范式:CQG-Single单次生成一个检索查询,CQG-AR自回归生成连续残差更新,在保留逐步解码的同时移除了SID物品词表、代码查找及离散波束扩展。这些设计消除了有限波束解码导致的SID特定可达性约束,避免了将离散SID词表与预训练骨干网络向量空间对齐的技术挑战。两种方法均使每个编码物品可通过密集或近似最近邻检索直接评分。在采用有效前缀约束解码的统一协议下,CQG-Single在全部7次运行中均优于TIGER风格基线,且仅使用55.3%的可训练参数;CQG-AR在ML-1M数据集上表现相当,在Beauty和Sports数据集上数值表现更强。受控深度消融实验进一步表明,额外的连续优化不会单调提升浅层准确率。这些发现推动在评估生成式推荐系统时,将输出表示、自回归建模与检索预算解耦。

英文摘要:

Generative recommendation (GR) of social media platforms commonly retrieves items by autoregressively decoding discrete Semantic IDs (SIDs) with finite-width beam search. This work examines how this output interface constrains whether held-out targets enter finite returned lists, while distinguishing catalog-wide scoreability from empirical top-K support. We introduce two continuous-query paradigms: CQG-Single generates one retrieval query in a single pass, and CQG-AR autoregressively generates continuous residual updates, retaining step-wise decoding while removing the SID item-token vocabulary, code lookup, and discrete beam expansion. These designs thereby eliminate the SID-specific reachability constraint induced by finite-beam decoding and avoid the technical challenge of aligning a discrete SID vocabulary with the pretrained backbone's vector space. Both methods make every encoded item directly scoreable through dense or approximate-nearest-neighbor retrieval. Under a unified protocol with valid-prefix constrained decoding, CQG-Single exceeds the TIGER-style baseline in all seven runs while using 55.3% as many trainable parameters. CQG-AR remains comparable on ML-1M and is numerically stronger on Beauty and Sports datasets. A controlled depth ablation further shows that additional continuous refinement does not monotonically improve shallow accuracy. These findings motivate decoupling output representation, autoregressive modeling, and retrieval budget when evaluating generative recommendation systems.

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。

↑