Advancing Graph Neural Networks for Complex Relational Learning: A Multi-Scale Heterogeneity-Aware Framework with Adversarial Robustness and Interpretable Analysis

Hao Yang, Yunhong Zhou, Xianzhe Ji, Zifan Liu, Zhen Tian, Qiang Tang and Yanchao Shi ()
Additional contact information
Hao Yang: School of Mathematics and Computer Science, Panzhihua University, Jichang Rd, East District, Panzhihua 617000, China
Yunhong Zhou: School of Mathematics and Computational Science, Wuyi University, Jiangmen 529020, China
Xianzhe Ji: International Business School Suzhou, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China
Zifan Liu: School of Mathematics, Jilin University, Changchun 130012, China
Zhen Tian: James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK
Qiang Tang: School of Artificial Intelligence, Anhui University of Science and Technology, Hefei 231131, China
Yanchao Shi: School of Business, Linyi University, Shuangling Road, Lanshan District, Linyi 276000, China

Mathematics, 2025, vol. 13, issue 18, 1-27

Abstract: Graph Neural Networks (GNNs) face fundamental algorithmic challenges in real-world applications due to a combination of data heterogeneity, adversarial heterophily, and severe class imbalance. A critical research gap exists for a unified framework that can simultaneously address these issues, limiting the deployment of GNNs in high-stakes domains like financial fraud detection and social network analysis. This paper introduces HAG-CFNet, a novel framework designed to bridge this gap by integrating three key innovations: (1) a heterogeneity-aware message-passing mechanism that uses relation-specific attention to capture rich semantic information; (2) a dual-channel heterophily detection module that explicitly identifies and neutralizes adversarial camouflage through separate aggregation pathways; and (3) a domain-aware counterfactual generator that produces plausible, actionable explanations by co-optimizing feature and structural perturbations. These are supported by a synergistic imbalance correction strategy combining graph-adapted oversampling with cost-sensitive learning. Extensive testing on large-scale financial datasets validates the framework’s impact: HAG-CFNet achieves a 4.2% AUC-PR improvement over state-of-the-art methods, demonstrates superior robustness by reducing performance degradation under structural noise by over 50%, and generates counterfactual explanations with 91.8% validity while requiring minimal perturbations. These advances provide a direct pathway to building more trustworthy and effective AI systems for critical applications ranging from financial risk management to supply chain analysis and social media content moderation.

Keywords: graph neural networks; heterogeneous graph learning; message-passing algorithms; adversarial robustness; heterophily detection; interpretable machine learning; multi-scale graph analysis (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/18/2956/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/18/2956/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:18:p:2956-:d:1748116

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().