InfoGraph

InfoGraph copied to clipboard

When I look at : ``` error += (model(data) * std - data.y * std).abs().sum().item() # MAE ``` I am curious what the .sum is doing here? Aren't these just...

melnimr

About negative loss

2

Hi, I find that as the training goes (beyond 20 epochs), the loss will gradually become negative. May I ask if this is harmful to downstream tasks? Thank you!

zhikaili

Question about the data labels `y` in unsupervised learning

3

Hi, I am trying to run your framework on my own unlabeled dataset. However, as I looked into your code of the **unsupervised** section, I see in your `get_embedding()` function...

lindazha0