Feature Requests & Voting Hub

[zhengsx]

This issue is to maintain all features request on one page.

Note to contributors: If you want to work for a requested feature, re-open the linked issue. Everyone is welcome to work on any of the issues below.

Note to maintainers: All feature requests should be consolidated to this page. When there are new feature request issues, close them and create the new entries, with the link to the issues, in this page. The one exception is issues marked good first issue. these should be left open so they are discoverable by new contributors.

---

Call for voting

we would like to call the voting here, to prioritize these requests.
If you think a feature request is very necessary for you, you can vote for it by the following process:

got the issue (feature request) number.
search the number in this issue, check the voting of it exists or not.
if the voting exists, you can add 👍 to that voting
if the voting doesn't exist, you can create a new voting by replying to this thread, and add the number in the it.

---

Efficiency related

• High efficient shortest path implementation ([Feature Request] High Efficient Shortest Path Implementation #69 )
• Compact Pre-trained Graphormer-base on PCQM4M ([Feature Request] Compact pre-trained checkpoint on PCQM4Mv1/v2 without optimizer state.  #80 )

New features:

• Molecule Feature Extraction by RDKit ([Feature Request] Molecule Feature Extraction by RDKit #71 )

• Package Graphormer to PyPI ([Feature Request] Package Graphormer code for PyPI #72)

• Windows support (windows cannot run bash #144)

New algorithms:

• Examples of node classification and link prediction (Can Graphormer be modified to accommodate node classification and link prediction problems? #75 )

Objective and metric functions:

New pre-trained models:

• Pre-trained Graphormer v2.0 for ogbg-molpcba ([Feature Request] Pre-trained Graphormer v2.0 model for OGBG-MolPCBA #70 )
• Pre-trained Graphormer v2.0 on OC20 ([Feature Request] Pre-trained Graphormer v2.0 model on OC20 #73 )
• Pre-trained Graphormer-large v2.0 on PCAM4M ([Feature Request] Pre-trained Graphormer-large v2.0 on PCQM4M #74 )

Input enhancements:

• Sparse Graph Representation ([Feature request] Supports Sparse Graph Representation  #82 )

Bug fixs: