通过多尺度图抽象加速GNN训练，提升大规模图学习效率。
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
- 构建分层图表示与子图，实现跨尺度信息融合。
- 训练速度显著提升，大图任务下性能不降反升。
- 适合处理超大规模图数据的科研与工程人员。
图神经网络（GNN）在图结构数据学习中表现出强大能力，广泛应用于多个领域。然而，随着图规模和连通性的增加，传统GNN训练方法面临严重的计算与内存挑战，制约其可扩展性与效率。本文提出一种高效的GNN多尺度训练框架，利用分层图表示与子图，实现多尺度、多分辨率的信息集成。通过采用节点与边更少的粗粒度图抽象与子图，显著降低训练过程中的计算开销。基于该框架，我们设计了多种可扩展的训练策略，包括粗粒度到细粒度学习、子图到全图迁移以及多尺度梯度计算。我们还提供了部分理论分析，并在多种数据集与学习任务上验证了方法的有效性。结果表明，多尺度训练能大幅加速大规模图问题的GNN训练，同时保持甚至提升预测性能。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivity increase, standard GNN training methods face significant computational and memory challenges, limiting their scalability and efficiency. In this paper, we present a novel framework for efficient multiscale training of GNNs. Our approach leverages hierarchical graph representations and subgraphs, enabling the integration of information across multiple scales and resolutions. By utilizing coarser graph abstractions and subgraphs, each with fewer nodes and edges, we significantly reduce computational overhead during training. Building on this framework, we propose a suite of scalable training strategies, including coarse-to-fine learning, subgraph-to-full-graph transfer, and multiscale gradient computation. We also provide some theoretical analysis of our methods and demonstrate their effectiveness across various datasets and learning tasks. Our results show that multiscale training can substantially accelerate GNN training for large scale problems while maintaining, or even improving, predictive performance.
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。