Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kai Cheng, Hao Wang, Wei Guo, Weiwen Liu, Yong Liu, Yawen Li, Enhong Chen

TL;DR

A novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking that significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency and proposes a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items.

Abstract

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.

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

TL;DR

A novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking that significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency and proposes a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items.

Abstract

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.
Paper Structure (34 sections, 13 equations, 4 figures, 5 tables)

This paper contains 34 sections, 13 equations, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Reranking Method
  4. Personalized Reranking Method
  5. Semi-autoregressive Generation
  6. Preliminary
  7. Definition1. (Reranking Problem)
  8. Definition 2. (Generative Reranking)
  9. Methodology
  10. Encoder
  11. Embedding Layer
  12. Shared Encoder
  13. Generator and Online Distillation
  14. Semi-Autoregressive Generation
  15. Online Knowledge Distillation
  16. ...and 19 more sections

Figures (4)

  • Figure 1: Two challenges faced by generative reranking methods.
  • Figure 2: The overall framework of PSAD and its sub-modules.
  • Figure 3: Hyper-Parameter Performance
  • Figure 4: Performance comparison of item–user feature interaction mechanisms across user sequences with varying activity levels.