Skip to content
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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Early stopping for gat #743

Open
EtoDemerzel0427 opened this issue Aug 6, 2019 · 5 comments
Assignees
Labels

Comments

@EtoDemerzel0427
Copy link

@EtoDemerzel0427 EtoDemerzel0427 commented Aug 6, 2019

馃殌 Feature

Add early stopping mechanism for GAT.

Motivation

Noticed that the performance of GAT on CiteSeer and Pubmed is lower than the reported results in the paper. And after checking the issues of the official implementation, I noticed some people have asked about this, and the author said this is due to early stopping(Check this and this).

Alternatives

None.

Pitch

You may add one command line argument to enable early stopping, since for Cora it is needless.

@jermainewang

This comment has been minimized.

Copy link
Member

@jermainewang jermainewang commented Aug 6, 2019

You are right. We should add this. @VoVAllen could you please help?

@derkbreeze

This comment has been minimized.

Copy link

@derkbreeze derkbreeze commented Aug 7, 2019

@jermainewang Hi Minjie, may I know what's the meaning of the labels in PPI dataset? Cause I noticed each node can have multiple 1's and zeros in it's label. I just wonder what's the meaning of different position's 1. e.g. a 121 dimension label can have [1 0 0 1 1 0 1 0 0...1 1 0 ]. I would appreciate if you can tell me.

@mufeili

This comment has been minimized.

Copy link
Member

@mufeili mufeili commented Aug 7, 2019

@derkbreeze To my knowledge, GraphSAGE is the first work to use that dataset and I'm quoting their description here:

We classify protein roles鈥攊n terms of their cellular functions from gene ontology鈥攊n various protein-protein interaction (PPI) graphs, with each graph corresponding to a different human tissue [41]. We use positional gene sets, motif gene sets and immunological signatures as features and gene ontology sets as labels (121 in total), collected from the Molecular Signatures Database [34]. The average graph contains 2373 nodes, with an average degree of 28.8. We train all algorithms on 20 graphs and then average prediction F1 scores on two test graphs (with two other graphs used for validation).

@VoVAllen

This comment has been minimized.

Copy link
Collaborator

@VoVAllen VoVAllen commented Aug 7, 2019

Thanks! I'll look into this

@derkbreeze

This comment has been minimized.

Copy link

@derkbreeze derkbreeze commented Aug 7, 2019

@derkbreeze To my knowledge, GraphSAGE is the first work to use that dataset and I'm quoting their description here:

We classify protein roles鈥攊n terms of their cellular functions from gene ontology鈥攊n various protein-protein interaction (PPI) graphs, with each graph corresponding to a different human tissue [41]. We use positional gene sets, motif gene sets and immunological signatures as features and gene ontology sets as labels (121 in total), collected from the Molecular Signatures Database [34]. The average graph contains 2373 nodes, with an average degree of 28.8. We train all algorithms on 20 graphs and then average prediction F1 scores on two test graphs (with two other graphs used for validation).

Thank you Mufei for your help!

@VoVAllen VoVAllen mentioned this issue Aug 9, 2019
0 of 6 tasks complete
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
5 participants
You can鈥檛 perform that action at this time.