Rhomboid Tiling for Geometric Graph Deep Learning
This addresses the problem of geometric feature extraction in graph learning for researchers and practitioners, representing a novel method rather than an incremental improvement.
The paper tackled the limitation of Graph Neural Networks (GNNs) in capturing geometric features in geometric graphs by proposing Rhomboid Tiling clustering and RTPool, a hierarchical pooling model, which outperformed 21 state-of-the-art competitors on all 7 benchmark datasets.
Graph Neural Networks (GNNs) have proven effective for learning from graph-structured data through their neighborhood-based message passing framework. Many hierarchical graph clustering pooling methods modify this framework by introducing clustering-based strategies, enabling the construction of more expressive and powerful models. However, all of these message passing framework heavily rely on the connectivity structure of graphs, limiting their ability to capture the rich geometric features inherent in geometric graphs. To address this, we propose Rhomboid Tiling (RT) clustering, a novel clustering method based on the rhomboid tiling structure, which performs clustering by leveraging the complex geometric information of the data and effectively extracts its higher-order geometric structures. Moreover, we design RTPool, a hierarchical graph clustering pooling model based on RT clustering for graph classification tasks. The proposed model demonstrates superior performance, outperforming 21 state-of-the-art competitors on all the 7 benchmark datasets.