A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)

TL;DR

This survey reviews how deep generative models are transforming recommender systems by enabling complex data modeling, natural language processing, and multimodal integration, while discussing evaluation paradigms and open challenges.

Contribution

It provides a comprehensive overview of recent advances in Gen-RecSys, connecting various generative approaches and highlighting future research directions.

Findings

Generative models enable modeling complex user-item interactions.

Large language models enhance natural language recommendations.

Multimodal models integrate images and videos into recommender systems.

Abstract

Traditional recommender systems (RS) typically use user-item rating histories as their main data source. However, deep generative models now have the capability to model and sample from complex data distributions, including user-item interactions, text, images, and videos, enabling novel recommendation tasks. This comprehensive, multidisciplinary survey connects key advancements in RS using Generative Models (Gen-RecSys), covering: interaction-driven generative models; the use of large language models (LLM) and textual data for natural language recommendation; and the integration of multimodal models for generating and processing images/videos in RS. Our work highlights necessary paradigms for evaluating the impact and harm of Gen-RecSys and identifies open challenges. This survey accompanies a tutorial presented at ACM KDD'24, with supporting materials provided at: https://encr.pw/vDhLq.