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

2026-01-06

arXiv.org

AI Summary

Existing graph prompt learning methods apply prompts across the full node feature dimension, often introducing redundancy and susceptibility to feature noise. This work proposes SpikingGPF, which, to the best of our knowledge, is the first to incorporate spiking neuron mechanisms into graph prompt learning. SpikingGPF generates sparse and selective prompt vectors for each node and leverages sparse representation theory to construct a lightweight yet robust prompting framework. The proposed method significantly enhances representation compactness and computational efficiency, consistently outperforming current graph prompting approaches in both performance and noise robustness across multiple benchmark datasets.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Prompt Engineering / Prompting
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Graph Prompting
• Spiking Neuron
• Feature Sparsity
• Node Feature Noise
• Prompt Redundancy

Innovation

• Spiking Neuron
• Graph Prompt Learning
• Sparse Prompting
• Prompt Representation
• GNN Adaptation