HyperDefender: A Robust Framework for Hyperbolic GNNs

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.

Authors

• Nikita Malik Bharti School of Telecommunication Technology and Management, Indian Institute of Technology, Delhi, India
• Rahul Gupta Department of Mathematics and Computing, Indian Institute of Technology, Delhi, India
• Sandeep Kumar Department of Electrical Engineering, Indian Institute of Technology, Delhi, India Bharti School of Telecommunication Technology and Management, Indian Institute of Technology, Delhi, India Yardi School of Artificial Intelligence, Indian Institute of Technology, Delhi, India

Keywords

No keywords are indexed for this paper.