Evidential deep learning and other feature requests

Dear Graphormer authors,

thanks for this great piece of software!
I have some feature requests.

Can you please add the functionality for evidential deep learning?
See article:
ACS Cent. Sci. 2021, 7, 8, 1356–1367

Please add the 10 smaller datasets from MoleculeNet to the benchmarks. They are ogbg-moltox21, ogbg-molbace, ogbg-molbbbp, ogbg-molclintox, ogbg-molmuv, ogbg-molsider, and ogbg-moltoxcast for (multi-task) binary classification, and ogbg-molesol, ogbg-molfreesolv, and ogbg-mollipo for regression.
See https://ogb.stanford.edu/docs/graphprop/

Please add functionality for molecular representation pre-training via attribute masking
See Strategies for Pre-training Graph Neural Networks

Please add metrics described in the Regression Metrics Guide

As the manual selection of parameters for a graph neural network is difficult, please add support
for some of the automated machine learning techniques.
See for example techniques described in AutoGL

Many thanks.

No repository files, tests, or entry points are named. Start by separating the requests into independently scoped issues and locating the existing training, benchmarking, metrics, and pre-training entry points. Done should mean that one agreed feature is implemented with documented evaluation and tests or benchmark results.