用强化学习动态选重要节点，让图神经网络更快更准
BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks
- 用多臂赌博机动态选择每层最有信息量的邻居节点
- 在保持全量训练精度的同时，显著降低计算开销
- 适用于GCN和GAT，能自适应不同模型的聚合方式
图神经网络（GNN）在处理图结构数据时表现强大，但面对大规模图时受限于计算成本。传统方法需处理每个节点的所有邻居，导致内存和计算瓶颈。为此，我们提出BLISS——一种基于多臂赌博机的层间重要性采样策略。该方法在每层动态选择最具信息量的节点，通过平衡探索与利用，实现全面的图覆盖。相比静态采样方法，BLISS能随节点重要性变化自适应调整，提升节点选择准确性。其设计兼容图卷积网络（GCN）与图注意力网络（GAT），可根据不同聚合机制调整选择策略。实验表明，BLISS在保持或超越全批量训练精度的前提下，显著降低计算开销。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their application to large graphs is hindered by computational costs. The need to process every neighbor for each node creates memory and computational bottlenecks. To address this, we introduce BLISS, a Bandit Layer Importance Sampling Strategy. It uses multi-armed bandits to dynamically select the most informative nodes at each layer, balancing exploration and exploitation to ensure comprehensive graph coverage. Unlike existing static sampling methods, BLISS adapts to evolving node importance, leading to more informed node selection and improved performance. It demonstrates versatility by integrating with both Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), adapting its selection policy to their specific aggregation mechanisms. Experiments show that BLISS maintains or exceeds the accuracy of full-batch training.
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。