def forward(self, x, edge_index, edge_weight=None):
""""""
# edge_index, edge_weight = remove_self_loops(edge_index, edge_weight)
# print(x.size(), edge_index.size())
row, col = edge_index
batch, num_nodes, num_edges, K = x.size(0), x.size(1), row.size(
0), self.weight.size(0)
edge_weight = edge_weight.view(-1)
assert edge_weight.size(0) == edge_index.size(1)
###degree matrix
deg = scatter_add(edge_weight, row, dim=0, dim_size=num_nodes)
# Compute normalized and rescaled Laplacian.
deg = deg.pow(-0.5)
deg[torch.isinf(deg)] = 0
lap = -deg[row] * edge_weight * deg[col]
###Rescale the Laplacian eigenvalues in [-1, 1]
##rescale: 2L/lmax-I; lmax=1.0
fill_value = -0.05 ##-0.5
edge_index, lap = add_self_loops(edge_index, lap, fill_value,
num_nodes)
lap *= 2
########################################
# Perform filter operation recurrently.
Tx_0 = x
out = torch.matmul(Tx_0, self.weight[0])
if K > 1:
Tx_1 = spmm(edge_index, lap, num_nodes,
x.permute(1, 2, 0).contiguous().view(
(num_nodes, -1))).view(
(num_nodes, -1, batch)).permute(
2, 0,
1) # spmm(edge_index, lap, num_nodes, x)
out = out + torch.matmul(Tx_1, self.weight[1])
for k in range(2, K):
Tx_2 = 2 * spmm(
edge_index, lap, num_nodes,
x.permute(1, 2, 0).contiguous().view((num_nodes, -1))).view(
(num_nodes, -1, batch)).permute(2, 0, 1) - Tx_0
# 2 * spmm(edge_index, lap, num_nodes, Tx_1) - Tx_0
out = out + torch.matmul(Tx_2, self.weight[k])
Tx_0, Tx_1 = Tx_1, Tx_2
if self.bias is not None:
out = out + self.bias
return out
def forward(self, x, edge_index, edge_weight=None):
batch, num_nodes = x.size(0), x.size(1)
##first adjust the adj matrix with diag elements
edge_index, edge_weight = add_self_loops(edge_index, edge_weight, 1, num_nodes)
row, col = edge_index
edge_weight = edge_weight.view(-1)
assert edge_weight.size(0) == edge_index.size(1)
###degree matrix
deg = scatter_add(edge_weight, row, dim=0, dim_size=num_nodes)
# Compute normalized and rescaled Laplacian.
deg = deg.pow(-0.5)
deg[torch.isinf(deg)] = 0
lap = deg[row] * edge_weight * deg[col]
###Rescale the Laplacian eigenvalues in [-1, 1]
#fill_value = 0.05 ##-0.5
#edge_index, lap = add_self_loops(edge_index, lap, fill_value, num_nodes)
x = torch.matmul(x, self.weight)
out = spmm(edge_index, lap, num_nodes, x.permute(1, 2, 0).contiguous().view((num_nodes, -1))).view((num_nodes, -1, batch)).permute(2, 0,1) # spmm(edge_index, lap, num_nodes, x)
if self.bias is not None:
out = out + self.bias
return out
def forward(self, x, edge_index, edge_weight=None):
# type: (Tensor, Tensor, Optional[Tensor]) -> Tensor
edge_index, edge_weight = remove_self_loops(edge_index, edge_weight)
row, col = edge_index[0], edge_index[1]
num_nodes, num_edges, K = x.size(0), row.size(0), self.weight.size(0)
if edge_weight is None:
edge_weight = torch.ones((num_edges,),
dtype=x.dtype,
device=edge_index.device)
edge_weight = edge_weight.view(-1)
deg = scatter_add(edge_weight, row, dim=0, dim_size=num_nodes)
# Compute normalized and rescaled graph Laplacian
deg = deg.pow(-0.5)
lap = -deg[row] * edge_weight * deg[col]
# Perform filter operation recurrently
Tx_0 = x
out = torch.mm(Tx_0, self.weight[0])
Tx_1 = spmm(edge_index, lap, num_nodes, x)
if K > 1:
out = out + torch.mm(Tx_1, self.weight[1])
for k in range(K):
if k >= 2:
Tx_2 = 2 * spmm(edge_index, lap, num_nodes, Tx_1) - Tx_0
out = out + torch.mm(Tx_2, self.weight[k])
Tx_0, Tx_1 = Tx_1, Tx_2
if self.bias is not None:
out = out + self.bias
return out
