Spiking Graph Neural Network on Riemannian Manifolds
This work addresses energy efficiency and latency issues in graph learning for applications like robotics or bioinformatics, but it is incremental as it builds on existing spiking GNNs by incorporating manifold geometry.
The paper tackled the high computation and energy consumption of conventional graph neural networks (GNNs) and the high latency of existing spiking GNNs by proposing a manifold-valued spiking GNN (MSG) that operates on Riemannian manifolds, achieving superior performance to previous spiking GNNs and energy efficiency to conventional GNNs.
Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressive performance at the cost of high computation and energy consumption. In parallel, spiking GNNs with brain-like spiking neurons are drawing increasing research attention owing to the energy efficiency. So far, existing spiking GNNs consider graphs in Euclidean space, ignoring the structural geometry, and suffer from the high latency issue due to Back-Propagation-Through-Time (BPTT) with the surrogate gradient. In light of the aforementioned issues, we are devoted to exploring spiking GNN on Riemannian manifolds, and present a Manifold-valued Spiking GNN (MSG). In particular, we design a new spiking neuron on geodesically complete manifolds with the diffeomorphism, so that BPTT regarding the spikes is replaced by the proposed differentiation via manifold. Theoretically, we show that MSG approximates a solver of the manifold ordinary differential equation. Extensive experiments on common graphs show the proposed MSG achieves superior performance to previous spiking GNNs and energy efficiency to conventional GNNs.