lylbaidu / agnn Goto Github PK

请问大佬，如何通过ml100k\source_data——》生成模型训练所需的数据的？可否更新上传数据处理代码？

In standard VAE, it's item_var instead of item_z,
kl_loss = torch.mean(0.5 * torch.sum(torch.exp(item_z) + item_mu ** 2 - 1. - item_var, 1)) +
torch.mean(0.5 * torch.sum(torch.exp(user_z) + user_mu ** 2 - 1. - user_var, 1))

"""
Hence we require the reconstructed embedding x′u to be similar with both the preference embed- ding (by the constraint) and the original attribute distribution (by the standard VAE). To summarize, the reconstruction loss function in our proposed eVAE is defined as follows.

where the first two terms are same as those in standard VAE, and the last one is our extension for the approximation part.
"""

can you share processed movielens-1M dataset? Thanks!

hi,dear
as the title, and the U-U graph and the I-I graph are from where ??

could you please help me ?
thx