提出消除邻居冗余信息聚合，解决GCN深层化中的过平滑问题。
Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
- 发现高阶邻居消息传递必经低阶邻居，导致信息重复聚合。
- 揭示过聚合是过平滑的根本原因，而非仅靠残差连接可解决。
- 为构建更深更有效的GCN提供新思路，适合图神经网络研究者。
近年来，图卷积网络（GCNs）因其处理图结构数据的优异能力而广受欢迎。现有基于GCN的方法通常采用浅层模型架构，以应对过平滑现象。当前缓解过平滑的方法主要通过在GCN架构中添加额外组件，如残差连接和随机边丢弃策略。然而，这些改进对构建深层GCN的效果有限。本文分析了GCN内在的消息传递机制，识别出一个关键问题：来自高阶邻居的信息必须经过低阶邻居才能到达目标节点。这种对低阶邻居的反复依赖导致了冗余信息聚合，我们称之为过聚合。分析表明，过聚合不仅引入显著冗余，更是GCN中过平滑的根本原因。
原文摘要 · Abstract (English)
In recent years, Graph Convolutional Networks (GCNs) have gained popularity for their exceptional ability to process graph-structured data. Existing GCN-based approaches typically employ a shallow model architecture due to the over-smoothing phenomenon. Current approaches to mitigating over-smoothing primarily involve adding supplementary components to GCN architectures, such as residual connections and random edge-dropping strategies. However, these improvements toward deep GCNs have achieved only limited success. In this work, we analyze the intrinsic message passing mechanism of GCNs and identify a critical issue: messages originating from high-order neighbors must traverse through low-order neighbors to reach the target node. This repeated reliance on low-order neighbors leads to redundant information aggregation, a phenomenon we term over-aggregation. Our analysis demonstrates that over-aggregation not only introduces significant redundancy but also serves as the fundamental cause of over-smoothing in GCNs.
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。