$P^2$GNN: Two Prototype Sets to boost GNN Performance

TL;DR

$P^2$GNN introduces a prototype-based method to enhance message passing in GNNs by incorporating global context and denoising, significantly improving performance across diverse datasets and tasks.

Contribution

The paper proposes a novel, plug-and-play prototype technique for GNNs that enhances global context and noise robustness, applicable to all message-passing GNNs.

Findings

Outperforms existing models in e-commerce recommendation tasks.

Achieves top average rank on multiple open-source datasets.

Qualitative analysis confirms the benefits of global context and noise mitigation.

Abstract

Message Passing Graph Neural Networks (MP-GNNs) have garnered attention for addressing various industry challenges, such as user recommendation and fraud detection. However, they face two major hurdles: (1) heavy reliance on local context, often lacking information about the global context or graph-level features, and (2) assumption of strong homophily among connected nodes, struggling with noisy local neighborhoods. To tackle these, we introduce $P^2$GNN, a plug-and-play technique leveraging prototypes to optimize message passing, enhancing the performance of the base GNN model. Our approach views the prototypes in two ways: (1) as universally accessible neighbors for all nodes, enriching global context, and (2) aligning messages to clustered prototypes, offering a denoising effect. We demonstrate the extensibility of our proposed method to all message-passing GNNs and conduct extensive experiments across 18 datasets, including proprietary e-commerce datasets and open-source datasets, on node recommendation and node classification tasks. Results show that $P^2$GNN outperforms production models in e-commerce and achieves the top average rank on open-source datasets, establishing it as a leading approach. Qualitative analysis supports the value of global context and noise mitigation in the local neighborhood in enhancing performance.