HyperDefender: A Robust Framework for Hyperbolic GNNs
Nikita Malik, Rahul Gupta, Sandeep Kumar
Abstract
Graph neural networks for hyperbolic space has emerged as a powerful tool for embedding datasets exhibiting a highly non-Euclidean latent anatomy e.g., graphs with hierarchical structures. While several Hyperbolic Graph Neural Networks (Hy-GNNs) have been developed to enhance the representation of hierarchical datasets, they remain susceptible to noise and adversarial attacks, posing serious risks in critical applications. The absence of robust Hy-GNN frameworks underscores a pressing problem. This research addresses this challenge by introducing HyperDefender—a robust and flexible approach designed to fortify Hy-GNNs against adversarial attacks and noises. HyperDefender aims to secure the reliability of applications that depend on the integrity of hierarchical graph-structured data in real-world scenarios. Experimental results demonstrate that HyperDefender significantly improves node classification accuracy across various attacks, effectively mitigating the performance degradation typically observed in Hy-GNNs when the hierarchy in original datasets is compromised.
BibTeX
@article{Malik_Gupta_Kumar_2025, title={HyperDefender: A Robust Framework for Hyperbolic GNNs}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34135}, DOI={10.1609/aaai.v39i18.34135}, abstractNote={Graph neural networks for hyperbolic space has emerged as a powerful tool for embedding datasets exhibiting a highly non-Euclidean latent anatomy e.g., graphs with hierarchical structures. While several Hyperbolic Graph Neural Networks (Hy-GNNs) have been developed to enhance the representation of hierarchical datasets, they remain susceptible to noise and adversarial attacks, posing serious risks in critical applications. The absence of robust Hy-GNN frameworks underscores a pressing problem. This research addresses this challenge by introducing HyperDefender—a robust and flexible approach designed to fortify Hy-GNNs against adversarial attacks and noises. HyperDefender aims to secure the reliability of applications that depend on the integrity of hierarchical graph-structured data in real-world scenarios. Experimental results demonstrate that HyperDefender significantly improves node classification accuracy across various attacks, effectively mitigating the performance degradation typically observed in Hy-GNNs when the hierarchy in original datasets is compromised.}, number={18}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Malik, Nikita and Gupta, Rahul and Kumar, Sandeep}, year={2025}, month={Apr.}, pages={19396-19404} }