针对图神经网络过平滑问题，提出基于图结构的新型权重初始化方法。
Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks
- 基于图拓扑设计权重初始化，改进传统方法忽略图结构的问题。
- 在无特征节点的冷启动场景下，深度模型性能显著优于浅层模型。
- 理论分析与实验验证结合，适用于需要深层图网络的任务。
本文将Kaiming初始化思想推广至图神经网络（GNN），提出一种新初始化方法（G-Init），有效缓解深层网络中的过平滑问题，在节点分类和图分类任务中表现优异。现有GNN常沿用其他神经网络的初始化方法，忽视了图结构特性。我们理论上分析了卷积型GNN中信号前向传播与梯度反向传播的方差，并简化至GCN情形，推导出新初始化方案。结果表明，该方法能有效减少深层GNN的过平滑现象，提升模型实用性。实验验证支持理论发现，在无特征节点的冷启动场景下，深度网络仍能取得优越性能。
原文摘要 · Abstract (English)
In this work, we generalize the ideas of Kaiming initialization to Graph Neural Networks (GNNs) and propose a new scheme (G-Init) that reduces oversmoothing, leading to very good results in node and graph classification tasks. GNNs are commonly initialized using methods designed for other types of Neural Networks, overlooking the underlying graph topology. We analyze theoretically the variance of signals flowing forward and gradients flowing backward in the class of convolutional GNNs. We then simplify our analysis to the case of the GCN and propose a new initialization method. Our results indicate that the new method (G-Init) reduces oversmoothing in deep GNNs, facilitating their effective use. Experimental validation supports our theoretical findings, demonstrating the advantages of deep networks in scenarios with no feature information for unlabeled nodes (i.e., ``cold start'' scenario).
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。