用泊松过程实现动态节点更新，缓解图神经网络过平滑问题。
P-DROP: Poisson-Based Dropout for Graph Neural Networks
- 基于泊松时钟实现异步局部更新，保持结构多样性。
- 在Cora等数据集上优于传统Dropout、DropEdge等方法，尤其在训练后期更优。
- 适合追求模型稳定性和泛化能力的图学习研究者。
过平滑仍是图神经网络的主要挑战，重复的消息传递导致节点表示趋于收敛，丧失区分能力。为此，我们提出一种基于泊松过程的新节点选择策略，实现随机但结构感知的更新。具体而言，为每个节点配置独立的泊松时钟，实现异步且局部化的更新，以保留结构多样性。我们探索了该策略的两种应用：作为基于丢弃的正则化替代方案，以及动态子图训练方案。在标准基准数据集（Cora、Citeseer、Pubmed）上的实验表明，我们的泊松基方法相比传统丢弃方法（Dropout、DropEdge、DropNode）取得了相当或更优的精度，尤其在训练后期表现更佳。
原文摘要 · Abstract (English)
Over-smoothing remains a major challenge in Graph Neural Networks (GNNs), where repeated message passing causes node representations to converge and lose discriminative power. To address this, we propose a novel node selection strategy based on Poisson processes, introducing stochastic but structure-aware updates. Specifically, we equip each node with an independent Poisson clock, enabling asynchronous and localized updates that preserve structural diversity. We explore two applications of this strategy: as a replacement for dropout-based regularization and as a dynamic subgraph training scheme. Experimental results on standard benchmarks (Cora, Citeseer, Pubmed) demonstrate that our Poisson-based method yields competitive or improved accuracy compared to traditional Dropout, DropEdge, and DropNode approaches, particularly in later training stages.
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。