DeepSVDD get 84% AUROC on SWaT, better than GANF
Closed this issue · 1 comments
I'm following your great work. However, when I run the DeepSVDD provided in the code, I get 84% AUROC on SWaT, better than GANF. It seems that DeepSVDD overfits the dataset. How can I solve this? The settings are as follows. I wish you can provide the setting of DeepSVDD so that I can continue following your great work. Thank you very much.
epochs = 40
input_feature = 51
hidden_size = 64
If possible, could you send your trianing code for baseline models to my email zhouqihang716@gmail.com
The training of DeepSVDD can be tricky. There are several factors can affect such as whether pretraining or not. The number training epochs. And we also observe that the random seed can affect a lot due to its sensitivity to the initialization. I will share the code to you.