✅ Correctness issue #62
Replies: 3 comments 7 replies
-
GAT correctnessThe logs of training GAT is as follows The training logs of Seastar GAT (#7) prior to all of our modifications was |
Beta Was this translation helpful? Give feedback.
-
GCN Correctness
|
Beta Was this translation helpful? Give feedback.
-
TGCN correctnessRealized that we were making a very major blunder by assuming that The updated logs for seastar graph training are as follows While the training is not as smooth as that of PyG-T, it works sufficiently well. I believe the smoothness in PyG-T is again attributed to the implementation of PyG GCN and any optimization/initialization there, which we can ignore for now. Hence that closes this discussion here. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
We believe that there is an issue of correctness, evident from the disparity of training logs between Seastar and PyG-T. This discussion will attempt to resolve that.
The logs are as follows
Beta Was this translation helpful? Give feedback.
All reactions