Please kindly disclose all the hyper-parameters you tuned, and how much you tuned for each of them. Please follow the following form: "lr: [0.001*, 0.01], num_layers: [4*,5], hidden_channels: [128, 256*], dropout: [0*, 0.5], epochs: early-stop*", where the asterisks denote the hyper-parameters you eventually selected (based on validation performance) to report the test performance. This information will not appear in the leaderboard for the time being, but it is important for us to keep the record and encourage the fair model selection.
Did you use model ensemble? If you did, we recommend you submitting the single model performance as well.
Hardware (GPU/TPU etc)
Test-dev inference time
All the information provided here is correct, and my submission follows the rules set by OGB-LSC. I understand that I cannot delete my leaderboard submission once it is public. Whenever I am contacted by the OGB-LSC Team, I need to provide information to verify the correctness of the information. Otherwise, the submission may be deleted, and future submissions may be prohibited.