Citation network datasets for benchmarking spiking graph neural networks on experimental neuromorphic hardware
Open Access
- 1 June 2026
- journal article
- research article
- Published by Springer Nature in npj Unconventional Computing
- Vol. 3 (1) , 23
Abstract
Spiking neural networks (SNNs) running on neuromorphic computers offer an energy-efficient alternative for AI tasks. Recently, spiking graph neural networks (S-GNNs) have been shown to produce encouraging results on benchmark citation network datasets such as Cora, CiteSeer, and PubMed for node classification tasks. These S-GNNs were run on SNN simulators only because they contain up to tens of thousands of neurons and up to millions of synapses, translating poorly to neuromorphic hardware. Therefore, in this paper, we create a suite of benchmark datasets from the CiteSeer dataset that can be accommodated on current neuromorphic hardware platforms. Our contribution consists of a collection of three datasets. First, we have an induced subgraph of CiteSeer, which we call MiniSeer, containing 2110 papers, 3604 binary features, and 6 topics. Second, MicroSeer is a very small dataset consisting of 84 papers, 1227 features, and 6 topics. Lastly, BiteSeer is a collection of 15 binary classification datasets. We present creation of these datasets along with accuracies, running times, and spike counts when simulated. We believe that our results in this paper will be used by the neuromorphic community to benchmark, test, and develop neuromorphic hardware and simulators.Keywords
Funding Information
- U.S. Department of Energy (DE-SC0025349)
- U.S. Department of Energy (DE-SC0025654)
- U.S. Department of Energy (DE-AC05-00OR22725)
- U.S. Department of Energy (DE-SC0025654)
- U.S. Department of Energy (DE-SC0025349)
- U.S. Department of Energy (DE-AC05-00OR22725)
- U.S. Department of Energy (DE-AC05-00OR22725)
- U.S. Department of Energy (DE-AC05-00OR22725)
- U.S. Department of Energy (DE-AC05-00OR22725)
- U.S. Department of Energy (DE-SC0025654)
- U.S. Department of Energy (DE-SC0025349)
- U.S. Department of Energy (DE-AC05-00OR22725)
This publication has 33 references indexed in Scilit:
- Spiking Transformer with Spatial-Temporal Attention2025
- A Suppression-based STDP Rule Resilient to Jitter Noise in Spike Patterns for Neuromorphic Computing2024
- DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processorNeuromorphic Computing and Engineering, 2024
- Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation2023
- Scaling deep learning for materials discoveryNature, 2023
- Financial fraud detection using graph neural networks: A systematic reviewExpert Systems with Applications, 2023
- From Ferroelectric Material Optimization to Neuromorphic DevicesAdvanced Materials, 2023
- Benchmarking the performance of neuromorphic and spiking neural network simulatorsNeurocomputing, 2021
- Design of Superconducting Optoelectronic Networks for Neuromorphic Computing2018
- Fast unfolding of communities in large networksJournal of Statistical Mechanics: Theory and Experiment, 2008