Hypergraph Isomorphism Network for Robustness Prediction

This paper addresses the limitations of existing deep learning methods in assessing the robustness of complex systems, particularly those modeled as hypergraphs. It proposes a novel Hypergraph Isomorphism Network (HWL-HIN) that leverages the expressive power of the Hypergraph Weisfeiler-Lehman test. This is significant because it offers a more accurate and efficient way to predict robustness compared to traditional methods and existing HGNNs, which is crucial for engineering and economic applications.

• •Proposes a Hypergraph Isomorphism Network (HWL-HIN) for hypergraph learning.
• •Theoretically equivalent to the Hypergraph Weisfeiler-Lehman test.
• •Outperforms existing graph-based models and HGNNs in robustness prediction.
• •Offers superior efficiency in training and prediction.