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 2107.04713cs.LGcs.CV
收藏

基于种群自调整GCN的自动图学习

Automated Graph Learning via Population Based Self-Tuning GCN

University of Georgia(佐治亚大学);Santa Clara University(圣克拉拉大学);Alibaba Group(阿里巴巴集团)

Ronghang Zhu, Zhiqiang Tao, Yaliang Li, Sheng Li

摘要:

图卷积网络(GCN)及其变体由于具有提取有效图嵌入的显著能力而被成功地应用于广泛的任务,例如节点分类、链接预测和图分类。传统的GCN模型存在过拟合和过平滑的问题,而最近的一些技术(如DropEdge)可以缓解这些问题,从而实现深度GCN的开发。然而,训练GCN模型是不平凡的,因为它对超参数的选择很敏感,例如辍学率和学习权重衰减,特别是对于深度GCN模型。在本文中,我们的目标是通过超参数优化来自动化GCN模型的训练。具体来说,我们提出了一个自调整的GCN方法与交替的训练算法,并进一步扩展我们的方法,将人口为基础的训练计划。与几个有代表性的基线相比,三个基准数据集上的实验结果证明了我们的方法在优化多层GCN方面的有效性。

英文摘要:

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several 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。

↑