EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks

Abstract

Graph Neural Networks (GNNs) have shown superior performance in analyzing attributed networks in various web-based applications such as social recommendation and web search. Nevertheless, in high-stake decision-making scenarios such as online fraud detection, there is an increasing societal concern that GNNs could make discriminatory decisions towards certain demographic groups. Despite recent explorations on fair GNNs, these works are tailored for a specific GNN model. However, myriads of GNN variants have been proposed for different applications, and it is costly to fine-tune existing debiasing algorithms for each specific GNN architecture. Different from existing works that debias GNN models, we aim to debias the input attributed network to achieve fairer GNNs through feeding GNNs with less biased data. Specifically, we propose novel definitions and metrics to measure the bias in an attributed network, which leads to the optimization objective to mitigate bias. We then develop a framework EDITS to mitigate the bias in attributed networks while maintaining the performance of GNNs in downstream tasks. EDITS works in a model-agnostic manner, i.e., it is independent of any specific GNN. Experiments 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.

Published at The Web Conference 2022 (WWW 2022)

References in corpus (13)

• Semi-Supervised Classification with Graph Convolutional Networks
• Equality of Opportunity in Supervised Learning
• Variational Graph Auto-Encoders
• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Fairness in Machine Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
• Compositional Fairness Constraints for Graph Embeddings
• Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
• Towards a Unified Framework for Fair and Stable Graph Representation Learning
• All of the Fairness for Edge Prediction with Optimal Transport
• Incorporating Priors with Feature Attribution on Text Classification

Cited by in corpus (14)

• A Comprehensive Survey on Deep Graph Representation Learning
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Towards Fair Graph Neural Networks via Graph Counterfactual
• Predicting Information Pathways Across Online Communities
• A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems
• Counterfactual Learning on Graphs: A Survey
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
• Endowing Pre-trained Graph Models with Provable Fairness
• FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
• Fairness without Demographics through Learning Graph of Gradients