GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection

Abstract

Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper, we propose a new graph neural network architecture that substitutes classical message passing with an analysis of the local distribution of node features. To this end, we extract the distribution of features in the egonet for each local neighbourhood and compare them against a set of learned label distributions by taking the histogram intersection kernel. The similarity information is then propagated to other nodes in the network, effectively creating a message passing-like mechanism where the message is determined by the ensemble of the features. We perform an ablation study to evaluate the network's performance under different choices of its hyper-parameters. Finally, we test our model on standard graph classification and regression benchmarks, and we find that it outperforms widely used alternative approaches, including both graph kernels and graph neural networks.

References in corpus (10)

• A Comprehensive Survey on Graph Neural Networks
• Hierarchical Graph Representation Learning with Differentiable Pooling
• A Survey on Graph Kernels
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
• Graph Clustering with Graph Neural Networks
• Testing Relational Understanding in Text-Guided Image Generation
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• On Graph Classification Networks, Datasets and Baselines

Cited by in corpus (1)

• Graph Kernel Neural Networks