LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training

TL;DR

LoRAP introduces a low-rank prompting method that significantly improves the performance of quantized graph neural networks by optimizing aggregation results with minimal additional computation.

Contribution

The paper proposes Low-Rank Aggregation Prompting (LoRAP), a novel input-dependent prompting technique that enhances quantization-aware training of GNNs.

Findings

LoRAP consistently improves quantized GNN performance across multiple frameworks.

The method introduces minimal computational overhead.

Experimental results on diverse datasets validate the effectiveness of LoRAP.

Abstract

Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to quantization in LLMs, quantizing graph features is more emphasized in GNNs. Inspired by the above, we propose to leverage prompt learning, which manipulates the input data, to improve the performance of quantization-aware training (QAT) for GNNs. To mitigate the issue that prompting the node features alone can only make part of the quantized aggregation result optimal, we introduce Low-Rank Aggregation Prompting (LoRAP), which injects lightweight, input-dependent prompts into each aggregated feature to optimize the results of quantized aggregations. Extensive evaluations on 4 leading QAT frameworks over 9 graph datasets demonstrate that LoRAP consistently enhances the performance of low-bit quantized GNNs while introducing a minimal computational overhead.