Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fairness and Diversity in Recommender Systems: A Survey

Yuying Zhao, Yu Wang, Yunchao Liu, Xueqi Cheng, Charu Aggarwal, Tyler Derr

TL;DR

This survey re-interprets fairness studies from the viewpoint of diversity, and expands the understanding of diversity to encompass not only the item level but also the user level.

Abstract

Recommender systems are effective tools for mitigating information overload and have seen extensive applications across various domains. However, the single focus on utility goals proves to be inadequate in addressing real-world concerns, leading to increasing attention to fairness-aware and diversity-aware recommender systems. While most existing studies explore fairness and diversity independently, we identify strong connections between these two domains. In this survey, we first discuss each of them individually and then dive into their connections. Additionally, motivated by the concepts of user-level and item-level fairness, we broaden the understanding of diversity to encompass not only the item level but also the user level. With this expanded perspective on user and item-level diversity, we re-interpret fairness studies from the viewpoint of diversity. This fresh perspective enhances our understanding of fairness-related work and paves the way for potential future research directions. Papers discussed in this survey along with public code links are available at https://github.com/YuyingZhao/Awesome-Fairness-and-Diversity-Papers-in-Recommender-Systems .

Fairness and Diversity in Recommender Systems: A Survey

TL;DR

This survey re-interprets fairness studies from the viewpoint of diversity, and expands the understanding of diversity to encompass not only the item level but also the user level.

Abstract

Recommender systems are effective tools for mitigating information overload and have seen extensive applications across various domains. However, the single focus on utility goals proves to be inadequate in addressing real-world concerns, leading to increasing attention to fairness-aware and diversity-aware recommender systems. While most existing studies explore fairness and diversity independently, we identify strong connections between these two domains. In this survey, we first discuss each of them individually and then dive into their connections. Additionally, motivated by the concepts of user-level and item-level fairness, we broaden the understanding of diversity to encompass not only the item level but also the user level. With this expanded perspective on user and item-level diversity, we re-interpret fairness studies from the viewpoint of diversity. This fresh perspective enhances our understanding of fairness-related work and paves the way for potential future research directions. Papers discussed in this survey along with public code links are available at https://github.com/YuyingZhao/Awesome-Fairness-and-Diversity-Papers-in-Recommender-Systems .
Paper Structure (29 sections, 17 equations, 4 figures, 3 tables, 1 algorithm)

This paper contains 29 sections, 17 equations, 4 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Recommender System Preliminaries
  3. Fairness in Recommender Systems
  4. Fairness Measurements
  5. Item-Level Fairness
  6. User-Level Fairness
  7. Debiasing Methods
  8. Pre-processing Methods
  9. In-processing Methods
  10. Post-processing Methods
  11. Diversity in Recommender Systems
  12. Source of Item Diversity
  13. Measurements to Quantify Item Diversity
  14. Individual Diversity
  15. Aggregate Diversity
  16. ...and 14 more sections

Figures (4)

  • Figure 1: (a) Fairness in Recommender Systems: fairness measurements and debiasing methods. (b) Diversity in Recommender Systems: diversity measurements and methods to enhance diversity.
  • Figure 2: Fairness and Diversity in RS: users are expected to be treated fairly despite their differences.
  • Figure 3: (A) A toy example to show the difference between individual and aggregate diversity; (B) A toy example to show the connection between aggregate diversity and exposure fairness. Different shapes correspond to different categories, colors correspond to different items, and levels of the darkness of the same color correspond to different levels of popularity (the darker color indicates the more popular item).
  • Figure 4: Fairness and Diversity: in the context of recommender systems, they are commonly investigated separately. However, the connections at item and user level highlight the significance of intersections.

Theorems & Definitions (10)

  • Definition 3.1
  • Definition 3.2
  • Definition 3.3
  • Definition 3.4
  • Definition 3.5
  • Definition 3.6
  • Definition 4.1
  • Definition 4.2
  • Definition 4.3
  • Definition 4.4