Please provide the version of OGB package you used for reporting the results. Make sure you used the required package version for the dataset of interest. Example: "1.3.6"

Please provide the name of the method, e.g., "GCN", "GraphSAGE", "GAT", "GIN" (maximum character count is 30).

When building your model, did you use external data (in the form of external pre-trained models, raw text, external unlabeled/labeled data)? If "Yes", please clearly indicate that in your method name above, e.g., GIN (pre-trained on PubChem).

Please provide the name of the dataset (e.g., "ogbn-products") that you would like the report the performance.

For the chosen dataset, please report the raw test performance output by the OGB evaluator. Please follow the following example format when reporting the average and unbiased standard deviation. "0.783231,0.03131" Here, the average is 0.783231 and the standard deviation is 0.03131.

For the chosen dataset, please report the raw validation performance output by the OGB evaluator. Please follow the same format as the test performance.

Please provide your own name and a short affiliation name in parentheses, e.g., Geoffrey Hinton (UToronto)

Please provide your email to contact about the method/code.

Please provide the link to Github repository or directory that contains all the code/instruction/command to reproduce your submitted result. Placeholder is NOT allowed.

Please provide the link to the original paper that describes the method. If your method has any original component (e.g., even just combining existing methods XXX and YYY), you have to write a technical report describing it (e.g., how you exactly combined XXX and YYY).

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.

Is the implementation official (implementation by authors who proposed the method) or unofficial (re-implementation of the method by non-authors)?

The number of parameters of your model.

The hardware (primarily for GPU) used for the experiments, e.g., GeForce RTX 2080 (11GB GPU). If multiple GPUs are used, please specify so.

Please join the Google group (https://groups.google.com/forum/#!forum/open-graph-benchmark) to keep up to date with OGB. Below, please write down the email you used for the group. This is necessary for the submission to be valid.