<ul><li>Researchers propose a new method called Adversarial Curriculum Graph-Free Knowledge Distillation (ACGKD) for data-free knowledge distillation of graph neural networks.</li><li>ACGKD leverages the Binary Concrete distribution to model graph structures and introduces a spatial complexity tuning parameter, reducing the spatial complexity of pseudo-graphs.</li><li>The proposed method accelerates the distillation process by enabling efficient gradient computation for the graph structure.</li><li>ACGKD achieves state-of-the-art performance in distilling knowledge from GNNs without training data.</li></ul>

Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks

Discover more