用结构感知编码初始化提升GNN性能，显著加快收敛并增强稳定性。
Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning
- 用统计学方法生成的图编码嵌入（GEE）作为节点特征初始值
- 在多数数据集上实现10%-50%的分类准确率提升
- 适合需要高效稳定训练的图神经网络应用场景
图神经网络（GNN）在众多节点级图学习任务中表现出强大能力，但其性能通常依赖于随机或信息极少的初始特征表示，劣质初始化会导致收敛变慢和训练不稳。本文提出利用统计上合理的独热图编码嵌入（GEE）作为结构感知的高质量初始特征，集成到标准GNN中形成GEE驱动的GNN（GG）框架。在大量仿真和真实世界基准测试中，GG在无监督与有监督设置下均实现持续且显著的性能提升。针对节点分类，进一步提出GG-C，将GG与GEE输出拼接，优于现有方法，在多数数据集上实现约10%-50%的准确率提升。结果表明，基于原理的结构感知初始化对提升GNN的效率、稳定性和整体性能至关重要，使模型从一开始就更充分地利用图拓扑结构。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have emerged as a powerful framework for a wide range of node-level graph learning tasks. However, their performance typically depends on random or minimally informed initial feature representations, where poor initialization can lead to slower convergence and increased training instability. In this paper, we address this limitation by leveraging a statistically grounded one-hot graph encoder embedding (GEE) as a high-quality, structure-aware initialization for node features. Integrating GEE into standard GNNs yields the GEE-powered GNN (GG) framework. Across extensive simulations and real-world benchmarks, GG provides consistent and substantial performance gains in both unsupervised and supervised settings. For node classification, we further introduce GG-C, which concatenates the outputs of GG and GEE and outperforms competing methods, achieving roughly 10-50% accuracy improvements across most datasets. These results demonstrate the importance of principled, structure-aware initialization for improving the efficiency, stability, and overall performance of graph neural network architecture, enabling models to better exploit graph topology from the outset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。