只训练一层图卷积网络，能有效缓解节点嵌入过度平滑问题。
Partially Trained Graph Convolutional Networks Resist Oversmoothing
- 冻结大部分层，仅训练首层以生成有区分度的节点表示。
- 网络宽度越大，未训练部分产生的节点嵌入差异越明显。
- 适用于标签数据少、初始特征不足的冷启动场景。
本文研究了Kipf与Welling提出的观察：未训练的图卷积网络（GCN）也能生成有意义的节点嵌入。我们考察了仅训练单层而冻结其余层的情况，提出可预测未训练层对嵌入生成贡献的理论基础。结果表明，网络宽度影响节点嵌入在经过未训练部分后的差异性。此外，我们建立了部分训练的GCN与过度平滑之间的联系，证明其具备抑制过度平滑的能力。实验验证了理论结论，并展示了在缺乏标签节点特征信息的冷启动场景下，深度且抗平滑的网络所带来的优势。
原文摘要 · Abstract (English)
In this work we investigate an observation made by Kipf \& Welling, who suggested that untrained GCNs can generate meaningful node embeddings. In particular, we investigate the effect of training only a single layer of a GCN, while keeping the rest of the layers frozen. We propose a basis on which the effect of the untrained layers and their contribution to the generation of embeddings can be predicted. Moreover, we show that network width influences the dissimilarity of node embeddings produced after the initial node features pass through the untrained part of the model. Additionally, we establish a connection between partially trained GCNs and oversmoothing, showing that they are capable of reducing it. We verify our theoretical results experimentally and show the benefits of using deep networks that resist oversmoothing, in a ``cold start'' scenario, where there is a lack of feature information for unlabeled nodes.
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。