SPGNN: Recognizing Salient Subgraph Patterns via Enhanced Graph Convolution and Pooling

arXiv:2404.13655v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have revolutionized the field of machine learning on non-Euclidean data such as graphs and networks. GNNs effectively implement node representation learning through neighborhood aggregation and achieve impressive results in many graph-related tasks. However, most neighborhood aggregation approaches are summation-based, which can be problematic as they may not be sufficiently expressive to encode informative graph structures. Furthermore, though the graph pooling module is also of vital importance for graph learning, especially for …

abstract aggregation arxiv convolution cs.ai cs.lg data gnns graph graph neural networks graphs however machine machine learning networks neural networks node non-euclidean patterns pooling representation representation learning results tasks through type via