Neural Re-ranking in Multi-stage Recommender Systems: A Review
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
DeGRe: Dense-supervised Generative Reranking for Recommendation
DeGRe decouples offline exploration via a lookahead evaluator using beam search and cumulative regression to distill dense supervision into an online generator that approximates optimal reranking sequences with greedy...
-
Harmonizing Generative Retrieval and Ranking in Chain-of-Recommendation
RecoChain unifies generative candidate generation via hierarchical semantic IDs and SIM-based ranking in a single Transformer to improve top-K recommendation performance.
-
Fast and Feasible: Permutation-based Constrained Reranking for Revenue Maximization
PermR approximates constrained ILP revenue maximization via neighbor swaps, reaching 63% of optimal gains within latency bounds and delivering 2% revenue lift in a 56M-query online test.
-
Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking
Dual-Rerank fuses autoregressive and non-autoregressive generative reranking via knowledge distillation and uses list-wise decoupled RL optimization to improve whole-page utility and cut latency in industrial video search.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.