Graph Pooling via Ricci Flow
This work addresses the need for effective pooling layers in Graph Neural Networks for attributed graphs, representing an incremental advancement by extending existing Ricci flow approaches to incorporate node attributes.
The authors tackled the problem of graph pooling in Graph Neural Networks by introducing ORC-Pool, a method that integrates node attributes into geometric clustering using Ollivier's discrete Ricci curvature, enabling improved performance on attributed graphs without specifying concrete numerical results.
Graph Machine Learning often involves the clustering of nodes based on similarity structure encoded in the graph's topology and the nodes' attributes. On homophilous graphs, the integration of pooling layers has been shown to enhance the performance of Graph Neural Networks by accounting for inherent multi-scale structure. Here, similar nodes are grouped together to coarsen the graph and reduce the input size in subsequent layers in deeper architectures. In both settings, the underlying clustering approach can be implemented via graph pooling operators, which often rely on classical tools from Graph Theory. In this work, we introduce a graph pooling operator (ORC-Pool), which utilizes a characterization of the graph's geometry via Ollivier's discrete Ricci curvature and an associated geometric flow. Previous Ricci flow based clustering approaches have shown great promise across several domains, but are by construction unable to account for similarity structure encoded in the node attributes. However, in many ML applications, such information is vital for downstream tasks. ORC-Pool extends such clustering approaches to attributed graphs, allowing for the integration of geometric coarsening into Graph Neural Networks as a pooling layer.