microsoft/Graphormer

train from scratch on molecule datasets

Open

#39 opened on Nov 30, 2021

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (376 forks)auto 404
good first issue

Repository metrics

Stars
 (2,459 stars)
PR merge metrics
 (PR metrics pending)

Description

Hello, I am trying to use Graphormer on other commonly used datasets from MoleculeNet (https://moleculenet.org/datasets-1) to check the performance, such as BACE, BBBP, etc. I have used the default hparams in the script of molhiv, but the results are horrible...

  1. May I know have you tried your model on these datasets without pretrained model? And do you have any suggestions on the hparams for these datasets if we want to train from scratch? I am trying to find out why the results are so bad...
  2. For molhiv without pretrained model, I have tried with the provided script in the examples folder, with not adding the "checkpoint_path" argument, and train for 100 epochs. But the best val score is only around 0.763 and the corresponding test score is only 0.636... I don't know what goes wrong... May I know have you tried to use Graphormer directly on molhiv without pretrained model? How is the performance? Thank you.

Contributor guide

Research direction
Investigate hyperparameter tuning, data preprocessing, and model initialization for training Graphormer from scratch on MoleculeNet datasets. Compare with pretrained model performance and check if the default molhiv script needs adjustments for other datasets.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
Pythondeep learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50