Dual Node and Edge Fairness-Aware Graph Partition

TL;DR

This paper introduces a dual fairness-aware graph partitioning method that considers both node and edge balance, improving fairness in social network analysis and downstream tasks.

Contribution

It proposes a novel edge balance concept, analyzes its relation to node balance, and develops a co-embedding framework for dual fairness-aware graph partitioning.

Findings

Balanced partitions in terms of nodes and edges achieved.

Framework improves fairness in node classification and link prediction.

Validated on multiple social network datasets.

Abstract

Fair graph partition of social networks is a crucial step toward ensuring fair and non-discriminatory treatments in unsupervised user analysis. Current fair partition methods typically consider node balance, a notion pursuing a proportionally balanced number of nodes from all demographic groups, but ignore the bias induced by imbalanced edges in each cluster. To address this gap, we propose a notion edge balance to measure the proportion of edges connecting different demographic groups in clusters. We analyze the relations between node balance and edge balance, then with line graph transformations, we propose a co-embedding framework to learn dual node and edge fairness-aware representations for graph partition. We validate our framework through several social network datasets and observe balanced partition in terms of both nodes and edges along with good utility. Moreover, we demonstrate our fair partition can be used as pseudo labels to facilitate graph neural networks to behave fairly in node classification and link prediction tasks.