EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks

08/11/2021
by   Yushun Dong, et al.
0

Graph Neural Networks (GNNs) have recently demonstrated superior capability of tackling graph analytical problems in various applications. Nevertheless, with the wide-spreading practice of GNNs in high-stake decision-making processes, there is an increasing societal concern that GNNs could make discriminatory decisions that may be illegal towards certain demographic groups. Although some explorations have been made towards developing fair GNNs, existing approaches are tailored for a specific GNN model. However, in practical scenarios, myriads of GNN variants have been proposed for different tasks, and it is costly to train and fine-tune existing debiasing models for different GNNs. Also, bias in a trained model could originate from training data, while how to mitigate bias in the graph data is usually overlooked. In this work, different from existing work, we first propose novel definitions and metrics to measure the bias in an attributed network, which leads to the optimization objective to mitigate bias. Based on the optimization objective, we develop a framework named EDITS to mitigate the bias in attributed networks while preserving useful information. EDITS works in a model-agnostic manner, which means that it is independent of the specific GNNs applied for downstream tasks. Extensive experiments on both synthetic and real-world datasets demonstrate the validity of the proposed bias metrics and the superiority of EDITS on both bias mitigation and utility maintenance. Open-source implementation: https://github.com/yushundong/EDITS.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/25/2022

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

Graph Neural Networks (GNNs) have emerged as the leading paradigm for so...
research
06/24/2022

On Structural Explanation of Bias in Graph Neural Networks

Graph Neural Networks (GNNs) have shown satisfying performance in variou...
research
07/10/2023

Improving Fairness of Graph Neural Networks: A Graph Counterfactual Perspective

Graph neural networks have shown great ability in representation (GNNs) ...
research
01/25/2023

Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective

Recently, graph-based models designed for downstream tasks have signific...
research
05/27/2022

Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation

In general, to draw robust conclusions from a dataset, all the analyzed ...
research
05/20/2022

FairNorm: Fair and Fast Graph Neural Network Training

Graph neural networks (GNNs) have been demonstrated to achieve state-of-...
research
05/25/2022

TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature

Trust evaluation is critical for many applications such as cyber securit...

Please sign up or login with your details

Forgot password? Click here to reset