Graph Learning with Localized Neighborhood Fairness

TL;DR

This paper introduces a neighborhood fairness concept for graph learning, focusing on local fairness in node neighborhoods, and develops a flexible framework that improves fairness and accuracy across various graph tasks.

Contribution

It proposes a novel neighborhood fairness framework for local graph representation learning, addressing limitations of global fairness approaches, and applies it to multiple tasks including fair link prediction.

Findings

Improves fairness in graph representations and link prediction.

Enhances accuracy in majority of tested scenarios.

Flexible framework adaptable to various data constraints.

Abstract

Learning fair graph representations for downstream applications is becoming increasingly important, but existing work has mostly focused on improving fairness at the global level by either modifying the graph structure or objective function without taking into account the local neighborhood of a node. In this work, we formally introduce the notion of neighborhood fairness and develop a computational framework for learning such locally fair embeddings. We argue that the notion of neighborhood fairness is more appropriate since GNN-based models operate at the local neighborhood level of a node. Our neighborhood fairness framework has two main components that are flexible for learning fair graph representations from arbitrary data: the first aims to construct fair neighborhoods for any arbitrary node in a graph and the second enables adaption of these fair neighborhoods to better capture certain application or data-dependent constraints, such as allowing neighborhoods to be more biased towards certain attributes or neighbors in the graph.Furthermore, while link prediction has been extensively studied, we are the first to investigate the graph representation learning task of fair link classification. We demonstrate the effectiveness of the proposed neighborhood fairness framework for a variety of graph machine learning tasks including fair link prediction, link classification, and learning fair graph embeddings. Notably, our approach achieves not only better fairness but also increases the accuracy in the majority of cases across a wide variety of graphs, problem settings, and metrics.