Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information

By Enyan Dai, Suhang Wang. Web Search and Data Mining, 2020

328 citations recorded by the source corpus.

Graph neural networks (GNNs) have shown great power in modeling graph structured data. However, similar to other machine learning models, GNNs may make predictions biased on protected sensitive attributes, e.g., skin color and gender. Because machine learning algorithms including GNNs are trained to reflect the distribution of the training data which often contains historical bias towards sensitive attributes. In addition, the discrimination in GNNs can be magnified by graph structures and the message-passing mechanism. As a result, the applications of GNNs in sensitive domains such as crime rate prediction would be largely limited. Though extensive studies of fair classification have been conducted on i.i.d data, methods to address the problem of discrimination on non-i.i.d data are rather limited. Furthermore, the practical scenario of sparse annotations in sensitive attributes is rarely considered in existing works. Therefore, we study the novel and important problem of learning fair GNNs with limited sensitive attribute information. FairGNN is proposed to eliminate the bias of GNNs whilst maintaining high node classification accuracy by leveraging graph structures and limited sensitive information. Our theoretical analysis shows that FairGNN can ensure the fairness of GNNs under mild conditions given limited nodes with known sensitive attributes. Extensive experiments on real-world datasets also demonstrate the effectiveness of FairGNN in debiasing and keeping high accuracy.

Subfields: Artificial Intelligence, Safety Research

View Paper: https://www.semanticscholar.org/paper/0b33c9c2eec5e7a71e1c051ec76e601e76152146

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Yong Li
4. Chen Gao
5. Depeng Jin
6. Yu Zheng
7. Jianxin Chang
8. Yao Ma

In Safety Research

1. Xiang Wang
2. Xiangnan He

Citations in the corpus

• Graph Neural Networks in Recommender Systems: A Survey (2020, unknown): “FairGNN [27] employs an adversarial learning paradigm to eliminate the bias of GNN by leveraging graph structures and limited sensitive information.”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “Despite the power of graph data in recommendation, it might inherit or even amplify discrimination and the societal bias in recommendation [36, 147, 195].”
• Graph Neural Networks for Recommender System (2022, background): “The objectives mainly contain accuracy, and at the same time, diversity [25], explainability [20], and fairness [6] attract much attention as well.”
• Is Homophily a Necessity for Graph Neural Networks? (2021, background): “, 2018) and more, and when unchecked, suffer traditional machine learning unfairness issues (Dai and Wang, 2021).”