Work

Encoding Graph Topology with Randomized Ising Models

Year: 2025

Type: conference-paper

Abstract: The increasing popularity of deep learning on graphs has motivated the need for the co-design of hardware and graph representation models.We propose Randomized Ising Model (RIM), a reservoir computing model for encoding topological information of graph nodes, that is amenable to physical implementation via neuromorphic hardware.Our experiments demonstrate that RIM's node embeddings are able to provide sufficient topological information to be suitable to address node classification tasks, exhibiting an accuracy in line with Graph Echo State Networks.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-109

Authors: Domenico Tortorella, Antonio Brau, Alessio Micheli

Institution: University of Pisa

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: European Commission

Awards: G4508289328, G8409961469