When Prompting Meets Spiking: Graph Sparse Prompting via Spiking Graph Prompt Learning

TL;DR

This paper introduces Spiking Graph Prompt Feature (SpikingGPF), a novel method that employs spiking neuron mechanisms to learn sparse, robust prompts for graph neural networks, improving efficiency and noise resistance.

Contribution

It pioneers the use of spiking neurons for sparse graph prompt learning, enhancing prompt efficiency and robustness in GNNs.

Findings

SpikingGPF outperforms existing methods on benchmark datasets.

The approach improves robustness against node feature noise.

SpikingGPF achieves more compact and efficient prompt representations.

Abstract

Graph Prompt Feature (GPF) learning has been widely used in adapting pre-trained GNN model on the downstream task. GPFs first introduce some prompt atoms and then learns the optimal prompt vector for each graph node using the linear combination of prompt atoms. However, existing GPFs generally conduct prompting over node's all feature dimensions which is obviously redundant and also be sensitive to node feature noise. To overcome this issue, for the first time, this paper proposes learning sparse graph prompts by leveraging the spiking neuron mechanism, termed Spiking Graph Prompt Feature (SpikingGPF). Our approach is motivated by the observation that spiking neuron can perform inexpensive information processing and produce sparse outputs which naturally fits the task of our graph sparse prompting. Specifically, SpikingGPF has two main aspects. First, it learns a sparse prompt vector for each node by exploiting a spiking neuron architecture, enabling prompting on selective node features. This yields a more compact and lightweight prompting design while also improving robustness against node noise. Second, SpikingGPF introduces a novel prompt representation learning model based on sparse representation theory, i.e., it represents each node prompt as a sparse combination of prompt atoms. This encourages a more compact representation and also facilitates efficient computation. Extensive experiments on several benchmarks demonstrate the effectiveness and robustness of SpikingGPF.