Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap

Weizhi Zhang, Yuanchen Bei, Liangwei Yang, Henry Peng Zou, Peilin Zhou, Aiwei Liu, Yinghui Li, Hao Chen, Jianling Wang, Yu Wang, Feiran Huang, Sheng Zhou, Jiajun Bu, Allen Lin, James Caverlee, Fakhri Karray, Irwin King, Philip S. Yu

TL;DR

An exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models is conducted, aiming to provide new insights for both the research and industrial communities on CSR.

Abstract

Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large language models (LLMs) have achieved tremendous success and possess strong capabilities in modeling user and item information, providing new potential for cold-start recommendations. However, the research community on CSR still lacks a comprehensive review and reflection in this field. Based on this, in this paper, we stand in the context of the era of large language models and provide a comprehensive review and discussion on the roadmap, related literature, and future directions of CSR. Specifically, we have conducted an exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models, aiming to provide new insights for both the research and industrial communities on CSR. Related resources of cold-start recommendations are collected and continuously updated for the community in https://github.com/YuanchenBei/Awesome-Cold-Start-Recommendation.

Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap

TL;DR

An exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models is conducted, aiming to provide new insights for both the research and industrial communities on CSR.

Abstract

Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large language models (LLMs) have achieved tremendous success and possess strong capabilities in modeling user and item information, providing new potential for cold-start recommendations. However, the research community on CSR still lacks a comprehensive review and reflection in this field. Based on this, in this paper, we stand in the context of the era of large language models and provide a comprehensive review and discussion on the roadmap, related literature, and future directions of CSR. Specifically, we have conducted an exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models, aiming to provide new insights for both the research and industrial communities on CSR. Related resources of cold-start recommendations are collected and continuously updated for the community in https://github.com/YuanchenBei/Awesome-Cold-Start-Recommendation.
Paper Structure (59 sections, 8 figures, 2 tables)

This paper contains 59 sections, 8 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. Related Work
  3. Survey Methodology
  4. Contributions
  5. PRELIMINARIES
  6. Background
  7. Recommender Systems
  8. Cold-Start Recommendations
  9. Problem Definition
  10. General Problem Definition
  11. Task-Specific Problem Definition
  12. CONTENT FEATURES
  13. Data-Incomplete Learning
  14. Robust Co-Training
  15. Knowledge Alignment
  16. ...and 44 more sections

Figures (8)

  • Figure 1: Illustrations of the knowledge scope discussed in this survey.
  • Figure 2: Statistical information of current cold-start recommendation publications.
  • Figure 3: An overview of the taxonomy of this survey for existing cold-start recommendation models.
  • Figure 4: Comparison of warm-start and different cold-start recommendation problems.
  • Figure 5: Illustrations of different strategies of graph relation usage.
  • ...and 3 more figures