Leaderboard Submission Form for OGB-LSC

This is a Google form to submit your results on the OGB-LSC. You will provide basic information and your result on a chosen dataset.

Package Version
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: "1.3.2"
Method
Please provide the name/description of the method/approach (e.g, GraphSAGE+node2vec; maximum character count is 30).
Dataset
Team name
Please provide the team name (which will be shown on the leaderbaord).
Affiliations
Please provide the affiliations of your team. Multiple affiliations needs to be separated by "/". Example: "Stanford / Google"
Primary contact person
Please provide the name of the primary contact person.
Primary contact email
Please provide your email that you check daily to contact about the method/code. For each dataset, you can only submit once in a week with the same email address. Your submission will get rejected if you try multiple submissions in a row with the same email address.
Code
Please provide the link to Github repository or directory that contains all the code to reproduce your results. Placeholder is NOT allowed.
Technical report
Please provide a link to the paper/technical report that describes the approach. The link can be Arxiv or PDF uploaded on your Github repository. You can update your paper using the same link once the test result is out.
Validation performance
For the chosen dataset, please self-report the validation performance (on the official val split) output by the OGB evaluator.
Tuned hyper-parameters
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.
#Parameters
The number of parameters of your *single model*. Must be an integer.
Model ensembling
Did you use model ensemble? If you did, we recommend you submitting the single model performance as well.
Hardware (GPU/TPU etc)
Hardware (CPU)
Training time
Test-dev inference time
Google group
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.
Horner code
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.
Please upload your test prediction: