当前位置: X-MOL 学术arXiv.cs.LG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
arXiv - CS - Machine Learning Pub Date : 2020-07-06 , DOI: arxiv-2007.02901
P\'eter Mernyei, C\u{a}t\u{a}lina Cangea

We present Wiki-CS, a novel dataset derived from Wikipedia for benchmarking Graph Neural Networks. The dataset consists of nodes corresponding to Computer Science articles, with edges based on hyperlinks and 10 classes representing different branches of the field. We use the dataset to evaluate semi-supervised node classification and single-relation link prediction models. Our experiments show that these methods perform well on a new domain, with structural properties different from earlier benchmarks. The dataset is publicly available, along with the implementation of the data pipeline and the benchmark experiments, at https://github.com/pmernyei/wiki-cs-dataset .

中文翻译:

Wiki-CS:基于维基百科的图神经网络基准

我们提出了 Wiki-CS,这是一个源自维基百科的新数据集,用于对图神经网络进行基准测试。该数据集由对应于计算机科学文章的节点组成,边缘基于超链接和 10 个代表该领域不同分支的类。我们使用数据集来评估半监督节点分类和单关系链接预测模型。我们的实验表明,这些方法在新领域表现良好,其结构特性不同于早期的基准。该数据集以及数据管道和基准实验的实施在 https://github.com/pmernyei/wiki-cs-dataset 上是公开的。
更新日期:2020-07-07
down
wechat
bug