Closed shahjaidev closed 2 years ago
As a follow up to the previously asked issue: https://github.com/gusye1234/LightGCN-PyTorch/issues/4
The paper uses logsigmoid in the loss function, but the code uses softplus. Why is this the case? These do not seem to be mathematically equivalent.
https://pytorch.org/docs/stable/generated/torch.nn.Softplus.html
https://pytorch.org/docs/stable/generated/torch.nn.LogSigmoid.html
As a follow up to the previously asked issue: https://github.com/gusye1234/LightGCN-PyTorch/issues/4
The paper uses logsigmoid in the loss function, but the code uses softplus. Why is this the case? These do not seem to be mathematically equivalent.
https://pytorch.org/docs/stable/generated/torch.nn.Softplus.html
https://pytorch.org/docs/stable/generated/torch.nn.LogSigmoid.html