Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fairness Amidst Non-IID Graph Data: A Literature Review

Wenbin Zhang, Shuigeng Zhou, Toby Walsh, Jeremy C. Weiss

TL;DR

This survey reviews recent advancements in fairness amidst non‐IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification.

Abstract

The growing importance of understanding and addressing algorithmic bias in artificial intelligence (AI) has led to a surge in research on AI fairness, which often assumes that the underlying data is independent and identically distributed (IID). However, real-world data frequently exists in non-IID graph structures that capture connections among individual units. To effectively mitigate bias in AI systems, it is essential to bridge the gap between traditional fairness literature, designed for IID data, and the prevalence of non-IID graph data. This survey reviews recent advancements in fairness amidst non-IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification. In addition, available datasets and evaluation metrics for future research are identified, the limitations of existing work are highlighted, and promising future directions are proposed.

Fairness Amidst Non-IID Graph Data: A Literature Review

TL;DR

This survey reviews recent advancements in fairness amidst non‐IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification.

Abstract

The growing importance of understanding and addressing algorithmic bias in artificial intelligence (AI) has led to a surge in research on AI fairness, which often assumes that the underlying data is independent and identically distributed (IID). However, real-world data frequently exists in non-IID graph structures that capture connections among individual units. To effectively mitigate bias in AI systems, it is essential to bridge the gap between traditional fairness literature, designed for IID data, and the prevalence of non-IID graph data. This survey reviews recent advancements in fairness amidst non-IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification. In addition, available datasets and evaluation metrics for future research are identified, the limitations of existing work are highlighted, and promising future directions are proposed.
Paper Structure (17 sections, 2 equations, 2 figures, 2 tables)

This paper contains 17 sections, 2 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Preliminaries and Taxonomy
  3. Overview
  4. Quantifying Graph Unfairness
  5. Graph Individual Fairness Notions
  6. Graph Group Fairness Notions
  7. Other Notions and Discussions
  8. Mitigating Graph Unfairness
  9. Graph Individual Fairness Methods
  10. Graph Group Fairness Methods
  11. Other Methods and Discussions
  12. Datasets and Evaluation Metrics
  13. Limitations and Future Directions
  14. Conclusion
  15. Biography
  16. ...and 2 more sections

Figures (2)

  • Figure 1: An illustrative example of IIDness and fair IID learning vs. Non-IIDness and fair Non-IID graph learning: (a) Data problem; (b) and (d) Data representation comparison; (c) and (e) Mapping transformation comparison; (m) and (n): Output space of methods with different assumptions.
  • Figure 2: An overview of the proposed taxonomy fairness amidst non-IID graph data.