arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.04828cs.LG
收藏

通过随机路径图序列实现快速有效的GNN训练

Fast and Effective GNN Training through Sequences of Random Path Graphs

CENTAI Institute(CENTAI研究院);Eurecat(欧洲环境与技术中心);Google Research(谷歌研究院);Sapienza University(罗马大学)

Francesco Bonchi, Claudio Gentile, Francesco Paolo Nerini, André Panisson, Fabio Vitale

AI总结:

提出GERN框架,利用有效电阻生成随机路径图序列训练GNN,提升小训练集下的训练速度与测试精度,解决过拟合、过压缩和过平滑问题。

摘要:

我们提出了GERN,一种用于节点分类任务中训练GNN的新型可扩展框架,基于有效电阻(谱图理论中的标准工具)。我们的方法在一系列随机生成树(适当地转换为路径图)上逐步优化GNN权重,尽管这些路径图结构简单,但被证明保留了原始输入图的基本拓扑和节点信息。这些路径图的稀疏性大大减轻了GNN训练的计算负担。这不仅增强了可扩展性,而且在后续测试阶段提高了准确性,尤其是在小训练集场景下,这在实际中非常重要,因为在许多现实世界场景中标签可能难以获取。在这些设置中,我们的框架产生了非常好的结果,因为它有效对抗了当训练集较小时由过拟合引起的训练退化。我们的方法还解决了常见问题,如过压缩和过平滑,同时避免了欠到达现象。尽管我们的框架灵活且可部署在多种类型的GNN中,但在本文中,我们专注于图卷积网络,并在多个真实世界图基准上进行了广泛的实验研究,在这些基准上,我们在广泛的代表性基线池中同时实现了训练速度和测试准确率的提升。

英文摘要:

We present GERN, a novel scalable framework for training GNNs in node classification tasks, based on effective resistance, a standard tool in spectral graph theory. Our method progressively refines the GNN weights on a sequence of random spanning trees suitably transformed into path graphs which, despite their simplicity, are shown to retain essential topological and node information of the original input graph. The sparse nature of these path graphs substantially lightens the computational burden of GNN training. This not only enhances scalability but also improves accuracy in subsequent test phases, especially under small training set regimes, which are of great practical importance, as in many real-world scenarios labels may be hard to obtain. In these settings, our framework yields very good results as it effectively counters the training deterioration caused by overfitting when the training set is small. Our method also addresses common issues like over-squashing and over-smoothing while avoiding under-reaching phenomena. Although our framework is flexible and can be deployed in several types of GNNs, in this paper we focus on graph convolutional networks and carry out an extensive experimental investigation on a number of real-world graph benchmarks, where we achieve simultaneous improvement of training speed and test accuracy over a wide pool of representative baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑