Fix bugs in trainer

Customized trainer support & performance debugging

Add default argument support of trainer & model in solver

fix pyg default aggregation for features

fix bugs in fe

Temporarily override the get method for the PyG datasets to fix issue #10

Temporarily override the get method for the datasets provided by PyTorch-Geometric to make the AutoGL compatible with PyTorch-Geometric>=1.6.2.
For version 1.6.2 or higher, the PyG InMemoryDataset has an additional internal attribute __data_list__ by default. If an in-memory dataset has the attribute and it is not None, then the item in the given specific index will be directly returned without accessing the data property.
Besides, the PyG matainer rusty1s also mentioned that "accessing dataset.data is not recommended" in https://github.com/rusty1s/pytorch_geometric/issues/1984.
In other words, mutating the data property of InMemoryDataset is not recommended by the PyTorch-Geometric. However, the current version of AutoGL does modify the data property of dataset.
Thus the get method of the PyG provided datasets is overrided to delete the __data_list__ attribute in advance before calling the virtual get method, aiming to temporarily fix the compatibility issue.

In addition, the ModelNet10 and ModelNet40 datasets are significantly modified.

update e-mail

Fix bugs and update to v0.1.1
* fix bugs in ogb dataset support
* change data to dataset in solver and trainer
* fix AutoNE for node clf
* fix some typos

rename autograph to autogl

Fix following bugs in v0.1.0:
* ogb format bug in dataset
* change interface of nodeclf trainer from `Data` to `Dataset`
* fix bugs in AutoNE