G-Signatures: Global Graph Propagation With Randomized Signatures
This addresses a bottleneck in GNNs for tasks requiring global graph properties, offering a novel approach with potential domain-specific impact.
The paper tackles the problem of graph neural networks (GNNs) struggling with global graph properties due to over-smoothing, and introduces G-Signatures, a method that enables global graph propagation via randomized signatures, showing empirical advantages in classification and regression tasks.
Graph neural networks (GNNs) have evolved into one of the most popular deep learning architectures. However, GNNs suffer from over-smoothing node information and, therefore, struggle to solve tasks where global graph properties are relevant. We introduce G-Signatures, a novel graph learning method that enables global graph propagation via randomized signatures. G-Signatures use a new graph conversion concept to embed graph structured information which can be interpreted as paths in latent space. We further introduce the idea of latent space path mapping. This allows us to iteratively traverse latent space paths, and, thus globally process information. G-Signatures excel at extracting and processing global graph properties, and effectively scale to large graph problems. Empirically, we confirm the advantages of G-Signatures at several classification and regression tasks.