What question did this study set out to answer?

This work aims to develop a method for learning the controllability robustness of complex networks under batch attacks without lengthy simulations.

Diffusion Graph Transformer for Learning Controllability Robustness in Large-Scale Networks

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates controllability robustness in large-scale networks, suggesting efficient alternative to simulations.

This work aims to develop a method for learning the controllability robustness of complex networks under batch attacks without lengthy simulations.
Proposed diffusion graph transformer (DGT) generates embeddings from node degree attributes.
Transformed features are adaptively propagated via a designed diffusion strategy.
Final predictions are produced using a fully connected layer.
DGT shows excellent accuracy with significant speed advancements for controllability robustness learning.
DGT addresses controllability robustness for large-scale networks, applicable to networks of hundreds of thousands of nodes.
DGT offers strong transferability regarding varying attack batch sizes.

Ding et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates controllability robustness in large-scale networks, suggesting efficient alternative to simulations.

This work aims to develop a method for learning the controllability robustness of complex networks under batch attacks without lengthy simulations.
Proposed diffusion graph transformer (DGT) generates embeddings from node degree attributes.
Transformed features are adaptively propagated via a designed diffusion strategy.
Final predictions are produced using a fully connected layer.
DGT shows excellent accuracy with significant speed advancements for controllability robustness learning.
DGT addresses controllability robustness for large-scale networks, applicable to networks of hundreds of thousands of nodes.
DGT offers strong transferability regarding varying attack batch sizes.

Ding et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark