Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
This provides a domain-specific benchmark for evaluating Graph Neural Networks in semi-supervised node classification and link prediction tasks, but it is incremental as it applies existing methods to new data.
The authors introduced Wiki-CS, a new dataset from Wikipedia for benchmarking Graph Neural Networks, focusing on computer science articles with hyperlink-based edges and 10 classes, and found that existing methods perform well on this domain with distinct structural properties.
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 .