-
-
Notifications
You must be signed in to change notification settings - Fork 60
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
Some problems about topology loss #17
Comments
Hi, in the adjacency matrix, 1 represents the positive edge. But for calculating the loss, the prediction loss regards 0 as positive. |
Thank you for your reply, but if the network uses 0 as the positive class to calculate the loss, shouldn’t the topological network predict that 0 is the positive edge? Isn’t this the opposite of GT? |
In (1 - GT), the 0 means that the 0-th channel of the predicted adjacency matrix is positive, and we just have one channel on the predicted result. You can think about a multiclass classification problem that the number means that the instance belongs to the n-th class. |
Can I understand it this way, in the results predicted by the topology network, does 0 mean that there is a connection? |
No. In the predicted results, we got one channel, which's value is 0.8 for example, meaning the predicted edge is positive. Just take it another way, for a classification problem with 3 classes, the predicted confidence of an instance is [0.8, 0.1, 0.1], which means the instance is predicted as the 0-th, and the corresponding GT for calculating the loss is 0 (assuming the GT is 0-th class). |
But when calculating the loss, the value predicted by the network is compared with 0th. Doesn’t the 0 predicted by the network correspond to the 0th of GT? Doesn’t the value of 0 predicted by the network correspond to the connection of GT? |
I think 0 is not a value but a class in the (1 - GT). It is a loss for classification instead of regression. |
Thanks for your reply, I still have some questions. In (1-GT), class 0 is meaningful, which represents connected edges. Doesn’t the class 0 predicted by the topology network correspond to the class 0 of (1-GT)? |
For a positive edge in GT, the network should predict it as class 0, that's correct. And predicting the 0-th class means that the 0-th channel of the adjacency matrix should have greater values, then we use a threshold of > 0.5 to determine a predicted positive edge. |
Thank you! Your patience and clear explanation were incredibly helpful. |
Hello, when we looked at the baseline model, we found that the model will use 1-gt, and 0 as positive when calculating the topology loss. Why do you do this, shouldn’t 1 be positive?
The text was updated successfully, but these errors were encountered: