[Dataset] Contribute IGB-Homo dataset to node_classification.py

[BowenYao18]

Description

I added IGB-HOMO-dataset to the RGCN folder, currently it supports the three smaller version (tiny[~0.35GB], small[~3.5GB], medium[~35GB]).

Usage:

1. Run the "download.py --size {choose the size}", the dataset will be downloaded and processed under the default ""dataset/"" folder
2. Run the ""node_classification.py"" with the corresponding dataset you just processed

Checklist

Please feel free to remove inapplicable items for your PR.

• The PR title starts with [$CATEGORY] (such as [NN], [Model], [Doc], [Feature]])
• I've leverage the tools to beautify the python and c++ code.
• The PR is complete and small, read the Google eng practice (CL equals to PR) to understand more about small PR. In DGL, we consider PRs with less than 200 lines of core code change are small (example, test and documentation could be exempted).
• All changes have test coverage
• Code is well-documented
• To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
• Related issue is referred in this PR
• If the PR is for a new model/paper, I've updated the example index here.

Changes

[dgl-bot]

To trigger regression tests:

• @dgl-bot run [instance-type] [which tests] [compare-with-branch];
  For example: @dgl-bot run g4dn.4xlarge all dmlc/master or @dgl-bot run c5.9xlarge kernel,api dmlc/master

[dgl-bot]

Commit ID: c5285d1

Build ID: 1

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 418d06c

Build ID: 2

Status: ⚪️ CI test cancelled due to overrun.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 3d43ab8

Build ID: 3

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: df5c273

Build ID: 4

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 8a173ad

Build ID: 5

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: e6ec96f

Build ID: 6

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 81ba919

Build ID: 7

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 10c86e6

Build ID: 8

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 84eeac6

Build ID: 9

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 672ec87

Build ID: 10

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 0d94836

Build ID: 11

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: c00c51a55e888d9144c373d03a9bd99ae0248dc2

Build ID: 12

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 0861d8a

Build ID: 13

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: 1c65a7b

Build ID: 14

Status: ❌ CI test failed in Stage [Lint Check].

Report path: link

Full logs path: link

[dgl-bot]

Commit ID: f125d49

Build ID: 15

Status: ❌ CI test failed in Stage [Lint Check].

Report path: link

Full logs path: link

[mfbalin]

What is the timeline for the large and full variants of homo?

[dgl-bot]

Commit ID: b9616a1

Build ID: 16

Status: ❌ CI test failed in Stage [Lint Check].

Report path: link

Full logs path: link

[BowenYao18]

What is the timeline for the large and full variants of homo?

What do you mean by "timeline"?

[mfbalin]

What is the timeline for the large and full variants of homo?

What do you mean by "timeline"?

In this PR, you are adding the tiny, small and medium variants. When is the next PR expected?

[BowenYao18]

What is the timeline for the large and full variants of homo?

What do you mean by "timeline"?

In this PR, you are adding the tiny, small and medium variants. When is the next PR expected?

I don't know how long it will take for the large and full version of the hom dataset to be processed and uploaded to s3. (Since I need to reprepare the edge with self edge added) Probably need a week to run. If I also need to test whether the dataset is valid and runnable, it might take longer and I probably need to request a larger machine for running.

[dgl-bot]

Commit ID: 4f74219

Build ID: 17

Status: ✅ CI test succeeded.

Report path: link

Full logs path: link