<ul><li>Graph Neural Networks (GNNs) have achieved success in graph mining tasks.</li><li>Scaling GNNs to large graphs is challenging due to high computational and storage costs.</li><li>The random walk with noise masking (RMask) module addresses limitations of existing model-simplification works for GNNs.</li><li>RMask allows for exploring deeper GNNs while preserving scalability and achieving a good trade-off between accuracy and efficiency.</li></ul>

Towards Scalable and Deep Graph Neural Networks via Noise Masking

Discover more