• Home
  • Search
  • Bi-Level Selection via Meta Gradient for Graph-Based Fraud Detection
  • Cite Icon7
  • https://doi.org/10.1007/978-3-031-00123-9_31Copy DOI Icon

Bi-Level Selection via Meta Gradient for Graph-Based Fraud Detection

  • Jan 1, 2022
  • Linfeng Dong +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Graph Neural Networks (GNNs) have achieved remarkable successes by utilizing rich interactions in network data. When applied to fraud detection tasks, the scarcity and concealment of fraudsters bring two challenges: class imbalance and label noise. In addition to overfitting problem, they will compromise model performance through the message-passing mechanism of GNNs. For a fraudster in a neighborhood dominated by benign users, its learned representation will be distorted in the aggregation process. Noises will propagate through the topology structure as well. In this paper, we propose a Bi-Level Selection (BLS) algorithm to enhance GNNs under imbalanced and noisy scenarios observed from fraud detection. BLS learns to select instance-level and neighborhood-level valuable nodes via meta gradient of the loss on an unbiased clean validation set. By emphasizing BLS-selected nodes in the model training process, bias towards majority class (benign) and label noises will be suppressed. BLS can be applied on most GNNs with slight modifications. Experimental results on two real-world datasets demonstrate that BLS can significantly improve GNNs performance on graph-based fraud detection.KeywordsGraph Neural NetworkFraud detectionImbalanced learning

Similar Papers
  • Dissertation

Graph neural differential equation networks for improved representation learning and robustness

  • Jan 01, 2024
  • Kai Zhao
  • Research Article
  • Citations1

Graph Neural Networks with Coarse- and Fine-Grained Division for mitigating label noise and sparsity.

  • Jul 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Shuangjie Li +5
  • Research Article

Fortifying Robustness in Graph Neural Networks: A Loss Correction Approach to Mitigate Label Noise.

  • Mar 10, 2026
  • IEEE transactions on neural networks and learning systems
  • I-Chung Hsieh +1
  • Research Article
  • Citations21

Contrastive learning of graphs under label noise

  • Jan 06, 2024
  • Neural Networks
  • Xianxian Li +4
  • Research Article
  • Citations37

Fraud detection on multi-relation graphs via imbalanced and interactive learning

  • May 18, 2023
  • Information Sciences
  • Xiaodi Wang +3
  • Conference Article
  • Citations17

GraphDIVE: Graph Classification by Mixture of Diverse Experts

  • Jul 01, 2022
  • Fenyu Hu +5
  • Research Article
  • Citations3

A Systematic Study and Analysis of Graph Neural Networks under Noise

  • Jun 19, 2025
  • ACM Transactions on Knowledge Discovery from Data
  • Yufei Jin +1
  • Research Article
  • Citations1

HRGNN: Learning Holistically Robust Graph Neural Networks on Noisy Graphs with Label Scarcity

  • Feb 19, 2026
  • ACM Transactions on Intelligent Systems and Technology
  • Jun-Wei Chiu +1
  • Research Article
  • Citations11

Gradient-aware learning for joint biases: Label noise and class imbalance

  • Dec 18, 2023
  • Neural Networks
  • Shichuan Zhang +4
  • Research Article
  • Citations40

SCN_GNN: A GNN-based fraud detection algorithm combining strong node and graph topology information

  • Sep 22, 2023
  • Expert Systems with Applications
  • Jing Chen +5
  • Conference Article
  • Citations22

Learning Graph Neural Networks with Deep Graph Library

  • Apr 20, 2020
  • Da Zheng +4
  • Research Article
  • Citations2

GRAPH NEURAL NETWORK MODELS FOR DETECTING FRAUDULENT INSURANCE CLAIMS IN HEALTHCARE SYSTEMS

  • Mar 01, 2022
  • American Journal of Advanced Technology and Engineering Solutions
  • Md Tarek Hasan
  • Conference Article
  • Citations577

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

  • Oct 19, 2020
  • Yingtong Dou +5
  • Conference Article
  • Citations185

UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

  • Aug 01, 2021
  • Jing Huang +1
  • Dissertation

Learning Robust Graph Neural Networks with Limited Supervision

  • Jan 01, 2025
  • Abdullah Alchihabi
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.