Fair Graph Anomaly Detection via Multi-Disentangled Representation Processing
Open Access
- 6 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2719-2729
Abstract
No abstract availableFunding Information
- Specific Research Project of Guangxi for Research Bases and Talents, China (GuiKe AD24010011)
- Key Research & Development Program Project of Guangxi, China (GuiKe AB25069095)
- Australian Research Council, Australia (DP230101122)
This publication has 24 references indexed in Scilit:
- Toward fair graph neural networks via dual-teacher knowledge distillationNeural Networks, 2025
- Deep Graph Anomaly Detection: A Survey and New PerspectivesIEEE Transactions on Knowledge and Data Engineering, 2025
- Fairness in Graph Mining: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2023
- Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method2023
- Contrastive Attributed Network Anomaly Detection with Data Augmentation2022
- EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks2022
- FairOD: Fairness-aware Outlier Detection2021
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information2021
- Deep Anomaly Detection on Attributed Networks2019