FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
This addresses the issue of discriminatory outcomes in graph-based applications for users affected by bias, offering an efficient solution that is incremental over prior fairness methods.
The authors tackled the problem of biased graph representation learning by proposing FairMILE, a multi-level framework that efficiently learns fair graph representations, significantly reducing running time while achieving a superior fairness-utility trade-off compared to state-of-the-art baselines.
Graph representation learning models have demonstrated great capability in many real-world applications. Nevertheless, prior research indicates that these models can learn biased representations leading to discriminatory outcomes. A few works have been proposed to mitigate the bias in graph representations. However, most existing works require exceptional time and computing resources for training and fine-tuning. To this end, we study the problem of efficient fair graph representation learning and propose a novel framework FairMILE. FairMILE is a multi-level paradigm that can efficiently learn graph representations while enforcing fairness and preserving utility. It can work in conjunction with any unsupervised embedding approach and accommodate various fairness constraints. Extensive experiments across different downstream tasks demonstrate that FairMILE significantly outperforms state-of-the-art baselines in terms of running time while achieving a superior trade-off between fairness and utility.