Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Kai, Wang, Hao, Guo, Wei, Liu, Weiwen, Liu, Yong, Li, Yawen, Chen, Enhong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918378147414016
author Cheng, Kai
Wang, Hao
Guo, Wei
Liu, Weiwen
Liu, Yong
Li, Yawen
Chen, Enhong
author_facet Cheng, Kai
Wang, Hao
Guo, Wei
Liu, Weiwen
Liu, Yong
Li, Yawen
Chen, Enhong
contents Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07107
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
Cheng, Kai
Wang, Hao
Guo, Wei
Liu, Weiwen
Liu, Yong
Li, Yawen
Chen, Enhong
Information Retrieval
Artificial Intelligence
Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.
title Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2603.07107