Metrics
1 File views/ downloads
5 Record Views
Conference proceeding
EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
WWW '22: Proceedings of the ACM Web Conference 2022, pp.1259-1269
2022
Web of Science ID: WOS:000852713001031
Abstract
Graph Neural Networks (GNNs) have shown superior performance in analyzing attributed networks in various applications. 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.
Details
- Title
- EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
- Publication Details
- WWW '22: Proceedings of the ACM Web Conference 2022, pp.1259-1269
- Resource Type
- Conference proceeding
- Publisher
- Association for Computing Machinery (ACM)
- Number of pages
- 11
- Grant note
- Cisco Faculty Research Award 2006844 / Direct For Computer & Info Scie & Enginr; Div Of Information & Intelligent Systems; National Science Foundation (NSF); NSF - Directorate for Computer & Information Science & Engineering (CISE); NSF - Division of Information & Intelligent Systems (IIS) 2006844 / National Science Foundation (NSF)
- Copyright
- © 2022 Association for Computing Machinery.
- Identifiers
- WOS:000852713001031; 99381512041906600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English