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

• URL: http://arxiv.org/abs/2603.09195v1
• Date: Tue, 10 Mar 2026 05:10:02 GMT
• Title: $P^2$GNN: Two Prototype Sets to boost GNN Performance
• Abstract summary: We introduce $P2$GNN, a plug-and-play technique leveraging prototypes to optimize message passing.<n>We conduct extensive experiments across 18 datasets, including proprietary e-commerce datasets and open-source datasets.<n>Results show that $P2$GNN outperforms production models in e-commerce and achieves the top average rank on open-source datasets.
• Score: 16.94853903148634
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ADMP-GNN: Adaptive Depth Message Passing GNN [27.795209620648198]
  A key characteristic of Graph Neural Networks (GNNs) is their use of a fixed number of message-passing steps for all nodes.<n>We propose Adaptive Depth Message Passing GNN (ADMP-GNN), a novel framework that dynamically adjusts the number of message passing layers for each node.<n>We evaluate ADMP-GNN on the node classification task and observe performance improvements over baseline GNN models.
  arXiv  Detail & Related papers  (2025-09-01T06:42:19Z)
• Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning [17.31465642587528]
  Graph neural networks (GNNs) have emerged as a powerful framework for a wide range of node-level graph learning tasks.<n>In this paper, we leverage a statistically grounded method, one-hot graph encoder embedding (GEE), to generate high-quality initial node features.<n>We demonstrate its effectiveness through extensive simulations and real-world experiments across both unsupervised and supervised settings.
  arXiv  Detail & Related papers  (2025-07-15T21:01:54Z)
• Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation [59.4356484322228]
  Graph Neural Networks (GNNs) have shown promising performance in this domain.<n>We propose GNNs with Modality-Independent Receptive Fields, which employ separate GNNs with independent receptive fields.<n>Our results indicate that the optimal $K$ for certain modalities on specific datasets can be as low as 1 or 2, which may restrict the GNNs' capacity to capture global information.
  arXiv  Detail & Related papers  (2024-12-18T16:12:26Z)
• Learning Strong Graph Neural Networks with Weak Information [64.64996100343602]
  We develop a principled approach to the problem of graph learning with weak information (GLWI) We propose D$2$PT, a dual-channel GNN framework that performs long-range information propagation on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
  arXiv  Detail & Related papers  (2023-05-29T04:51:09Z)
• Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [58.76759997223951]
  We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs. We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
  arXiv  Detail & Related papers  (2022-03-19T14:26:43Z)
• Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators [14.573383849211773]
  Graph neural networks (GNNs) have achieved great success in many graph learning tasks. Existing GNNs mainly adopt either linear neighborhood aggregation (mean,sum) or max aggregator in their message propagation. We re-think the message propagation mechanism in GNNs and aim to develop the general nonlinear aggregators for neighborhood information aggregation in GNNs.
  arXiv  Detail & Related papers  (2022-02-18T11:49:59Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• Local Augmentation for Graph Neural Networks [78.48812244668017]
  We introduce the local augmentation, which enhances node features by its local subgraph structures. Based on the local augmentation, we further design a novel framework: LA-GNN, which can apply to any GNN models in a plug-and-play manner.
  arXiv  Detail & Related papers  (2021-09-08T18:10:08Z)
• Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
  Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
  arXiv  Detail & Related papers  (2020-06-26T17:03:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.