Exploiting Homeostatic Synaptic Modulation in Spiking Neural Networks for Semi-Supervised Graph Learning

Semi-supervised graph learning (SSL) is an important task in machine learning that aims to make predictions based on a limited amount of labeled data and a larger set of unlabeled structured data, which can be effectively processed by biological neural networks. In this paper, we investigate the effects of the underlying homeostatic synaptic modulation (HSM) in spiking neural networks (SNNs) on such scenario. We propose a novel framework that integrates HSM into the spiking graph convolutional network to maintain stability by regulating the strength of synapses based on the activity of neurons, allowing for stable graph learning in a semi-supervised setting. Experimental results on citation benchmark datasets demonstrate that the proposed HSM mechanism can enable SNNs with superior capabilities of convergence and generalization, meanwhile possessing expected characteristics of sparsity and call-back phenomenon. The proposed framework provides a promising approach for exploiting HSM in neural network architectures for efficient graph learning.