-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature] Adjusted homophily and label informativeness #6516
[Feature] Adjusted homophily and label informativeness #6516
Conversation
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for your contribution! I left a few comments, mainly on the documentation and the coding of loops over nodes and edges. Besides, you can add index to these measures here: https://github.com/dmlc/dgl/blob/master/docs/source/api/python/dgl.rst?plain=1#L207.
…ding to the new implementation
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
@rudongyu Thank you for your review and suggestions! I've rewritten the code to avoid loops, it's much faster now. Please take a look when you have time. |
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
0af72aa
to
0eedce6
Compare
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@OlegPlatonov Thank you for your contribution! The PR will be merged.
Co-authored-by: rudongyu <ru_dongyu@outlook.com>
Description
Hi! In a recent paper Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond several characteristics of labeled graphs have been proposed. First, it has been shown that a rarely used in graph ML literature measure named adjusted homophily satisfies more desirable properties than other homophily measures, which makes it appropriate for comparing homophily levels across datasets with different number of classes, class sizes, and degree distributions across classes. Further, a new characteristic - label informativeness - has been proposed. It shows how much information about a node's label we get from knowing its neighbor's label. It has been shown that label informativeness is much more correlated with GNN performance than homophily.
In this PR I've added adjusted homophily and label informativeness to DGL.
Checklist
Please feel free to remove inapplicable items for your PR.
Changes