Fairness-Aware Graph Representation Learning with Limited Demographic Information

TL;DR

This paper presents FairGLite, a novel framework for fair graph representation learning that operates effectively with limited demographic data, using proxy generation, adaptive confidence, and theoretical guarantees to mitigate bias.

Contribution

Introduces FairGLite, a framework that achieves bias mitigation with limited demographic info through proxy generation, adaptive strategies, and formal fairness guarantees.

Findings

Effective bias mitigation demonstrated across multiple datasets.

Maintains high utility while improving fairness metrics.

Provides theoretical bounds on fairness performance.

Abstract

Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of them assume full access to demographic information, a requirement rarely met in practice due to privacy, legal, or regulatory restrictions. To this end, this paper introduces a novel fair graph learning framework that mitigates bias in graph learning under limited demographic information. Specifically, we propose a mechanism guided by partial demographic data to generate proxies for demographic information and design a strategy that enforces consistent node embeddings across demographic groups. In addition, we develop an adaptive confidence strategy that dynamically adjusts each node's contribution to fairness and utility based on prediction confidence. We further provide theoretical analysis demonstrating that our framework, FairGLite, achieves provable upper bounds on group fairness metrics, offering formal guarantees for bias mitigation. Through extensive experiments on multiple datasets and fair graph learning frameworks, we demonstrate the framework's effectiveness in both mitigating bias and maintaining model utility.