models.py [35:54]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.dropout = dropout
        self.lin1 = Linear(hidden_channels, hidden_channels)
        self.lin2 = Linear(hidden_channels, 1)

    def reset_parameters(self):
        for conv in self.convs:
            conv.reset_parameters()

    def forward(self, z, edge_index, batch, x=None, edge_weight=None, node_id=None):
        z_emb = self.z_embedding(z)
        if z_emb.ndim == 3:  # in case z has multiple integer labels
            z_emb = z_emb.sum(dim=1)
        if self.use_feature and x is not None:
            x = torch.cat([z_emb, x.to(torch.float)], 1)
        else:
            x = z_emb
        if self.node_embedding is not None and node_id is not None:
            n_emb = self.node_embedding(node_id)
            x = torch.cat([x, n_emb], 1)
        for conv in self.convs[:-1]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models.py [95:114]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.dropout = dropout
        self.lin1 = Linear(hidden_channels, hidden_channels)
        self.lin2 = Linear(hidden_channels, 1)

    def reset_parameters(self):
        for conv in self.convs:
            conv.reset_parameters()

    def forward(self, z, edge_index, batch, x=None, edge_weight=None, node_id=None):
        z_emb = self.z_embedding(z)
        if z_emb.ndim == 3:  # in case z has multiple integer labels
            z_emb = z_emb.sum(dim=1)
        if self.use_feature and x is not None:
            x = torch.cat([z_emb, x.to(torch.float)], 1)
        else:
            x = z_emb
        if self.node_embedding is not None and node_id is not None:
            n_emb = self.node_embedding(node_id)
            x = torch.cat([x, n_emb], 1)
        for conv in self.convs[:-1]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -