Search papers, labs, and topics across Lattice.
The paper introduces $P^2$GNN, a plug-and-play technique that enhances message passing in Graph Neural Networks (GNNs) by incorporating two sets of prototypes. These prototypes serve to inject global context by acting as universally accessible neighbors and to denoise local neighborhoods by aligning messages to clustered prototypes. Experiments across 18 datasets, including e-commerce and open-source datasets, demonstrate that $P^2$GNN outperforms existing production models and achieves top average rank, highlighting its effectiveness in node recommendation and classification tasks.
$P^2$GNN's plug-and-play prototype approach boosts GNN performance by injecting global context and denoising local neighborhoods, achieving state-of-the-art results across diverse datasets.
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.
