用随机生成的基尔霍夫森林构建多尺度图表示，提升大图分类的效率与性能。
SHAKE-GNN: Scalable Hierarchical Kirchhoff-Forest Graph Neural Network
- 基于基尔霍夫森林构建分层随机多分辨率图分解，实现高效图表示。
- 在多个大规模图分类数据集上达到竞争性精度，且推理速度更快。
- 适合处理超大规模图数据的图分类任务，尤其关注效率与可扩展性。
图神经网络（GNN）在各类学习任务中取得了显著成功，但将其扩展到大规模图仍面临挑战，尤其在图级别任务中。本文提出SHAKE-GNN，一种基于分层基尔霍夫森林的新型可扩展图级GNN框架。基尔霍夫森林是一类用于构建图的随机多分辨率分解的随机生成树森林。SHAKE-GNN生成多尺度表征，支持在效率与性能之间灵活权衡。我们提出一种改进的数据驱动策略来选择权衡参数，并分析了SHAKE-GNN的时间复杂度。在多个大规模图分类基准测试中，SHAKE-GNN实现了具有竞争力的性能，同时展现出更优的可扩展性。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have achieved remarkable success across a range of learning tasks. However, scaling GNNs to large graphs remains a significant challenge, especially for graph-level tasks. In this work, we introduce SHAKE-GNN, a novel scalable graph-level GNN framework based on a hierarchy of Kirchhoff Forests, a class of random spanning forests used to construct stochastic multi-resolution decompositions of graphs. SHAKE-GNN produces multi-scale representations, enabling flexible trade-offs between efficiency and performance. We introduce an improved, data-driven strategy for selecting the trade-off parameter and analyse the time-complexity of SHAKE-GNN. Experimental results on multiple large-scale graph classification benchmarks demonstrate that SHAKE-GNN achieves competitive performance while offering improved scalability.
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。