Supplementary dataset for "Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking"

Juanhui Li, Harry Shomer, Haitao Mao, Shenglai Zeng, Yao Ma, Neil Shah, Jiliang Tang, Dawei YinZenodo 2023 · DOI · OpenAlex

Abstract

The supplementary dataset for the paper "Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking". We include the splits for cora, citeseer, and pubmed, the hard negative samples, and the node2vec embeddings. We also include a jupyter file <em>read_data.ipynb</em> to show how to read the non-txt file. heart_test_samples.npy, heart_valid_samples.npy: the heard negative samples *-n2v-embedding.pt: node2vec embeddings test_samples_index.pt, valid_samples_index.pt: the node index of the selected samples in ogbl-ppa under HeaRT gnn_feature: the input feature of cora, citeseer, pubmed More details for our code and how to use the dataset are on the code repository: https://github.com/Juanhui28/HeaRT .
BibTeX
@inproceedings{li2023supplementary,
  author = {Juanhui Li and Harry Shomer and Haitao Mao and Shenglai Zeng and Yao Ma and Neil Shah and Jiliang Tang and Dawei Yin},
  title = {{Supplementary dataset for "Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking"}},
  booktitle = {Zenodo},
  year = {2023},
  doi = {10.5281/zenodo.8226021},
}

Loading related content...

Figure