Neural Re-ranking in Multi-stage Recommender Systems: A Review

TL;DR

This paper reviews neural re-ranking methods in multi-stage recommender systems, discussing their taxonomy, development, benchmarks, and future directions, highlighting their impact on user experience and satisfaction.

Contribution

It provides a comprehensive taxonomy, performance benchmarks, and analysis of neural re-ranking algorithms, facilitating future research and industrial application improvements.

Findings

Neural re-ranking significantly improves recommendation quality.

Benchmark models show varying effectiveness across datasets.

Future research should focus on personalization and complexity management.

Abstract

As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications. This review aims at integrating re-ranking algorithms into a broader picture, and paving ways for more comprehensive solutions for future research. For this purpose, we first present a taxonomy of current methods on neural re-ranking. Then we give a description of these methods along with the historic development according to their objectives. The network structure, personalization, and complexity are also discussed and compared. Next, we provide benchmarks of the major neural re-ranking models and quantitatively analyze their re-ranking performance. Finally, the review concludes with a discussion on future prospects of this field. A list of papers discussed in this review, the benchmark datasets, our re-ranking library LibRerank, and detailed parameter settings are publicly available at https://github.com/LibRerank-Community/LibRerank.