A Comprehensive Survey on Retrieval Methods in Recommender Systems

TL;DR

This survey reviews the often-overlooked retrieval stage in recommender systems, focusing on similarity computation, indexing, training methods, benchmarking, and industrial applications to improve personalized recommendation efficiency.

Contribution

It provides a comprehensive overview of retrieval methods in recommender systems, highlighting recent advances, benchmarking results, and practical industrial case studies.

Findings

Benchmarking on three public datasets shows improved retrieval accuracy.

Industrial case study illustrates practical retrieval practices and challenges.

Enhanced indexing and training methods lead to more efficient retrieval processes.

Abstract

In an era dominated by information overload, effective recommender systems are essential for managing the deluge of data across digital platforms. Multi-stage cascade ranking systems are widely used in the industry, with retrieval and ranking being two typical stages. Retrieval methods sift through vast candidates to filter out irrelevant items, while ranking methods prioritize these candidates to present the most relevant items to users. Unlike studies focusing on the ranking stage, this survey explores the critical yet often overlooked retrieval stage of recommender systems. To achieve precise and efficient personalized retrieval, we summarize existing work in three key areas: improving similarity computation between user and item, enhancing indexing mechanisms for efficient retrieval, and optimizing training methods of retrieval. We also provide a comprehensive set of benchmarking experiments on three public datasets. Furthermore, we highlight current industrial applications through a case study on retrieval practices at a specific company, covering the entire retrieval process and online serving, along with practical implications and challenges. By detailing the retrieval stage, which is fundamental for effective recommendation, this survey aims to bridge the existing knowledge gap and serve as a cornerstone for researchers interested in optimizing this critical component of cascade recommender systems.