English

SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation

Information Retrieval 2026-08-03 v1

Abstract

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.

Cite

@article{arxiv.2608.02048,
  title  = {SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation},
  author = {Ziheng Zhang and Yu Cui and Bohao Wang and Yong He and Chao Yu and Chuan Yuan and Wujie Sun and Can Wang and Jiawei Chen},
  journal= {arXiv preprint arXiv:2608.02048},
  year   = {2026}
}

Comments

14 pages, 4 figures, 13 tables; includes appendices