Skip to yearly menu bar Skip to main content

Workshop: Graph Representation Learning and Beyond (GRL+)

Novel Applications: Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

P├ęter Mernyei


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. We will make the dataset publicly available for future work.

Teaser video |

Chat is not available.