SmartGR：面向生成式推荐的层级与束搜索感知知识蒸馏
SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation
AI总结：
该研究针对生成式推荐模型推理成本高的问题，提出SmartGR框架，通过层级感知SID蒸馏与束搜索感知排序蒸馏，在四个基准数据集上实现性能提升8.6%、平均推理速度提升2.39倍。
AI中文摘要：
生成式推荐（GR）已成为推荐系统中极具前景的范式。扩大GR模型规模可提升推荐性能，但会大幅增加推理成本。知识蒸馏是将大型GR模型的知识迁移至轻量模型的实用方案。不过，现有蒸馏方法未考虑GR特有的两大挑战：语义ID（SID）层级间蒸馏难度失衡，以及束搜索过程中前缀剪枝错误。为应对这些挑战，我们提出SmartGR，这是一种新型蒸馏框架，利用层级感知SID蒸馏迁移教师模型在层级间的建模能力，借助束搜索感知排序蒸馏在束搜索过程中蒸馏教师模型的排序偏好。在四个基准数据集上开展的大量实验验证了SmartGR的有效性与效率，其性能提升8.6%，平均推理速度提升2.39倍。
英文摘要：
Generative recommendation (GR) has emerged as a promising paradigm for recommender systems. Scaling up GR models can improve recommendation performance, but it also substantially increases inference cost. Knowledge distillation provides a practical solution by transferring knowledge from a large GR model to a lightweight one. However, existing distillation methods do not account for two GR-specific challenges: imbalanced distillation difficulty across the semantic ID (SID) hierarchy and incorrect prefix pruning during beam search. To address these challenges, we propose SmartGR, a novel distillation framework that utilizes Hierarchy-Aware SID Distillation to transfer the teacher's modeling capability across the hierarchy and leverages Beam-Aware Ranking Distillation to distill the teacher's ranking preferences during beam search. Extensive experiments on four benchmark datasets demonstrate the effectiveness and efficiency of SmartGR, improving the performance by 8.6% while achieving a 2.39$\times$ inference speedup on average.
