DHCF
- class dhg.models.DHCF(*args, **kwargs)[source]
Bases:
torch.nn.Module
The DHCF model proposed in Dual Channel Hypergraph Collaborative Filtering paper (KDD 2020).
Note
The user and item embeddings and trainable parameters are initialized with xavier_uniform distribution.
- Parameters
num_users (
int
) – The Number of users.num_items (
int
) – The Number of items.emb_dim (
int
) – Embedding dimension.num_layers (
int
) – The Number of layers. Defaults to3
.drop_rate (
float
) – The dropout probability. Defaults to0.5
.