GNN-LoFI: A novel graph neural network through localized feature-based histogram intersection

Alessandro Bicciato, Luca Cosmo, Giorgia Minello, Luca Rossi, Andrea Torsello

Research output: Journal article publicationJournal articleAcademic researchpeer-review


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.

Original languageEnglish
Article number110210
JournalPattern Recognition
Publication statusPublished - Apr 2024


  • Deep learning
  • Graph neural network

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'GNN-LoFI: A novel graph neural network through localized feature-based histogram intersection'. Together they form a unique fingerprint.

Cite this