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

2026-03-10

AI Summary

Message-passing graph neural networks (MP-GNNs) often suffer from limited global awareness due to their heavy reliance on local neighborhoods and exhibit degraded performance in heterogeneous or noisy environments. To address these limitations, this work proposes $P^2$GNN, a plug-and-play framework that introduces a dual-prototype mechanism into MP-GNNs for the first time. Specifically, one set of global prototypes acts as shared virtual neighbors across all nodes to enrich global context, while another set of local prototypes aligns and refines neighborhood messages. Notably, $P^2$GNN requires no modification to the backbone architecture and is compatible with any MP-GNN variant. Extensive experiments on 18 datasets—including both proprietary e-commerce and public benchmarks—demonstrate that $P^2$GNN consistently outperforms existing methods, achieving state-of-the-art average performance in node recommendation and classification tasks.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Social mining and social search on the Web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Message Passing GNNs
• local context
• global context
• homophily
• noisy neighborhoods

Innovation

• Prototype-based GNN
• Global Context Enhancement
• Local Neighborhood Denoising
• Message Passing Optimization
• Plug-and-Play GNN