def forward(self, data): # x has shape [N, in_channels] # edge_index has shape [2, E] # pdb.set_trace() x = data.x edge_index = data.edge_index batch = data.batch edge_attr = data.edge_attr x = F.relu(self.conv1(x, edge_index)) x, edge_index, edge_attr, batch, _, _ = self.pool1(x, edge_index, edge_attr, batch) x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1) x = F.relu(self.conv2(x, edge_index)) x, edge_index, edge_attr, batch, _, _ = self.pool2(x, edge_index, edge_attr, batch) x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1) x = F.relu(self.conv3(x, edge_index)) x, edge_index, edge_attr, batch, _, _ = self.pool3(x, edge_index, edge_attr, batch) x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1) x = x1 + x2 + x3 x = F.relu(self.lin1(x)) x = self.lin2(x) x = x.reshape(-1) return x
def forward(self, x, edge_index, batch, inference = False):
x = self.item_embedding(x)
x = x.squeeze(1)
x = F.leaky_relu(self.conv1(x, edge_index))
x, edge_index, _, batch, _, _= self.pool1(x, edge_index, None, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim = 1)
x = F.leaky_relu(self.conv2(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool2(x, edge_index, None, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim = 1)
x = F.leaky_relu(self.conv3(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool3(x, edge_index, None, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim = 1)
x = x1 + x2 + x3
x = self.lin1(x)
x = self.bn1(self.act1(x))
x = self.lin2(x)
x = self.bn2(self.act2(x))
x = F.dropout(x, p = 0.5, training = self.training)
x = self.lin3(x).squeeze(1)
if inference:
x_out = x1 + x2 + x3
return x, x_out
else:
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
edge_attr = None
x = F.relu(self.conv1(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch = self.pool1(x, edge_index, edge_attr,
batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch = self.pool2(x, edge_index, edge_attr,
batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_attr))
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(x1) + F.relu(x2) + F.relu(x3)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout, training=self.training)
x = F.relu(self.lin2(x))
x = F.dropout(x, p=self.dropout, training=self.training)
x = self.lin3(x)
pred = F.log_softmax(x, dim=-1)
if data.y is not None:
loss = F.nll_loss(pred, data.y)
return pred, loss
return pred, None
def forward(self, data, neg_num, samp_bias1, samp_bias2):
x, edge_index, batch = data.x, data.edge_index, data.batch
edge_attr = None
original_x = x
x = F.relu(self.conv1(x, edge_index, edge_attr))
# inputs: x, edge_index, edge_attr, batch, h, neg_num, samp_bias1, samp_bias2
x, edge_index, edge_attr, batch = self.pool1(x, edge_index, edge_attr, batch, original_x,
neg_num, samp_bias1, samp_bias2)
original_x = x
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch = self.pool2(x, edge_index, edge_attr, batch, original_x,
neg_num, samp_bias1, samp_bias2)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_attr))
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(x1) + F.relu(x2) + F.relu(x3)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.relu(self.lin2(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
if isinstance(edge_index, tuple):
edge_index = torch.stack(edge_index)
edge_attr = None
x = F.relu(self.conv1(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch = self.pool1(x, edge_index, edge_attr,
batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch = self.pool2(x, edge_index, edge_attr,
batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_attr))
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(x1) + F.relu(x2) + F.relu(x3)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout, training=self.training)
x = F.relu(self.lin2(x))
x = F.dropout(x, p=self.dropout, training=self.training)
pred = self.lin3(x)
return pred
def forward(self, x, edge_index, batch, edge_attr):
# edge_attr = edge_attr.squeeze()
# edge_index, edge_attr = self.augment_adj(edge_index, edge_attr, x.size(0))
x = self.conv1(x, edge_index)
if x.norm(p=2, dim=-1).min() == 0:
print('x is zeros')
x, edge_index, edge_attr, batch, perm, score1 = self.pool1(
x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
edge_attr = edge_attr.squeeze()
edge_index, edge_attr = self.augment_adj(edge_index, edge_attr,
x.size(0))
x = self.conv2(x, edge_index)
x, edge_index, edge_attr, batch, perm, score2 = self.pool2(
x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = torch.cat([x1, x2], dim=1) #concate
x = self.bn4(F.relu(self.fc1(x)))
x = F.dropout(x, p=0.5, training=self.training)
x = self.bn5(F.relu(self.fc2(x)))
x = F.dropout(x, p=0.5, training=self.training)
x = F.log_softmax(self.fc3(x), dim=-1)
return x, score1, score2
def forward(self, x, edge_index, batch=None):
if batch is None:
batch = torch.zeros(x.shape[0]).long()
x = F.relu(self.conv1(x, edge_index))
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
node_embs = x
x = x1 + x2 + x3
graph_emb = x
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.p, training=self.training)
x = F.relu(self.lin2(x))
x = self.lin3(x)
return x, (node_embs.detach(), graph_emb.detach())
def forward(self, data):
x, edge_index, batch = data.x.float(), data.edge_index.float(), data.batch.float()
x = F.relu(self.conv1(x.float(), edge_index.long()))
x1 = torch.cat([gmp(x.long(), batch.long()), gap(x.long(), batch.long())], dim=1)
x = F.relu(self.conv2(x.float(), edge_index.long()))
x2 = torch.cat([gmp(x.long(), batch.long()), gap(x.long(), batch.long())], dim=1)
x = F.relu(self.conv3(x.float(), edge_index.long()))
x, edge_index, _, batch, _,_ = self.pool3(x.long(), edge_index.long(), None, batch.long())
x3 = torch.cat([gmp(x.long(), batch.long()), gap(x.long(), batch.long())], dim=1)
x = x1 + x2 + x3
x = self.lin1(x)
x = self.act1(x)
x = self.lin2(x)
x = self.act2(x)
x = F.dropout(x, p=0.2, training=self.training)
x = torch.sigmoid(self.lin3(x)).squeeze(1)
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
if(self.training == True):
mask, torchmask = random_drop_node(self.node_per_graph, (int)(batch.size()[0] / self.node_per_graph), 0.75, 0.9)
x = x[mask]
batch = batch[mask]
edge_index, _ = subgraph(torchmask, edge_index, relabel_nodes = True)
x = self.linprev(x, edge_index)
x = F.relu(self.conv1(x, edge_index))
x = self.bn1(x)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x = self.bn2(x)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x = self.bn3(x)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv4(x, edge_index))
x = self.bn3(x)
x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = torch.cat([x1,x2,x3,x4], dim=1)
x = self.mlp(x)
x = F.log_softmax(x, dim=-1)
return x
def forward(self, data):
x, batch = data.x, data.batch
edge_index = knn_graph(x, 100, batch)
edge_index, _ = dropout_adj(edge_index, p=0.3)
batch = data.batch
x = F.leaky_relu(self.conv1(x, edge_index))
x1 = torch.cat([gap(x, batch), gmp(x, batch)], dim=1)
x = F.leaky_relu(self.conv2(x, edge_index))
x2 = torch.cat([gap(x, batch), gmp(x, batch)], dim=1)
x = F.leaky_relu(self.conv3(x, edge_index))
x3 = torch.cat([gap(x, batch), gmp(x, batch)], dim=1)
x = torch.cat([x1, x2, x3], dim=1)
x = self.batchnorm1(x)
x = F.leaky_relu(self.linear1(x))
x = self.drop(x)
x = F.leaky_relu(self.linear2(x))
x = F.leaky_relu(self.linear3(x))
x = F.leaky_relu(self.linear4(x))
x = F.leaky_relu(self.linear5(x))
x = self.out(x)
if self.classification:
x = torch.sigmoid(x)
x = x.view(-1)
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
edge_weight = None
x_out = 0
for idx in range(self.num_layers - 1):
self.edges.append(edge_index)
x, x_score = self.convs[idx](x, edge_index, edge_weight, batch)
x = F.relu(x) # x: [69403, 89] --> [69403, 128]
x, edge_index, edge_weight, batch = self.pool(
x, x_score, edge_index, edge_weight, batch) # x: [34769, 128]
x_ = torch.cat([gmp(x, batch), gap(x, batch)],
dim=1) # x1: [256, 256]
x_out += F.relu(x_)
x, x_score = self.convs[self.num_layers - 1](x, edge_index,
edge_weight, batch)
x = F.relu(x) # x: [69403, 89] --> [69403, 128]
x_ = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x_out += F.relu(x_)
x = F.relu(self.lin1(x_out))
x = F.relu(self.lin2(x))
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, **kwargs):
data = kwargs['x_grph']
data = NormalizeFeaturesV2()(data)
data = NormalizeEdgesV2()(data)
x, edge_index, edge_attr, batch = data.x, data.edge_index, data.edge_attr, data.batch
#x, edge_index, edge_attr, batch = data.x.type(torch.cuda.FloatTensor), data.edge_index.type(torch.cuda.LongTensor), data.edge_attr.type(torch.cuda.FloatTensor), data.batch
x = F.relu(self.conv1(x, edge_index))
x, edge_index, edge_attr, batch, _ = self.pool1(
x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x, edge_index, edge_attr, batch, _ = self.pool2(
x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, edge_attr, batch, _ = self.pool3(
x, edge_index, edge_attr, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout_rate, training=self.training)
features = F.relu(self.lin2(x))
out = self.lin3(features)
if self.act is not None:
out = self.act(out)
if isinstance(self.act, nn.Sigmoid):
out = out * self.output_range + self.output_shift
return features, out
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
x = self.item_embedding(x) # 初始化节点embedding
x = x.squeeze(1)
x = F.relu(self.conv1(x, edge_index)) # SAGEConv卷积
x, edge_index, _, batch, _ = self.pool1(
x, edge_index, None, batch) # TopK池化 保留 kN 个节点(k=ratio) 类似于Dropout
x1 = torch.cat([gmp(x, batch), gap(x, batch)],
dim=1) # shape:[*, 128x2=256]
x = F.relu(self.conv2(x, edge_index))
x, edge_index, _, batch, _ = self.pool2(x, edge_index, None, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, _, batch, _ = self.pool3(x, edge_index, None, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3 # shape:[*, 128x2=256]
x = self.lin1(x) # shape:[*, 128]
x = self.act1(x)
x = self.lin2(x) # shape:[*, 64]
x = self.act2(x)
x = F.dropout(x, p=0.5, training=self.training)
x = torch.sigmoid(self.lin3(x)).squeeze(1) # shape:[*, 1]
return x
def forward(self, x, edge_index, batch=None):
if len(x.shape
) == 3: #NEEDED FOR EXAI, NOTICE THAT IT MUST BE ONLY ONE MOL
data_list = []
for x_i, edge_index_i in zip(x, edge_index):
data_list.append(Data(x=x_i, edge_index=edge_index_i))
data = Batch.from_data_list(data_list).to(self.device)
x = data.x
batch = data.batch
edge_index = data.edge_index
shape = x.shape
x = x.reshape(-1, shape[-1])
x = self.atom_embedding(x)
x = x.reshape(shape)
x = x.squeeze(1)
x = F.relu(self.conv1(x, edge_index))
x, edge_index, batch, _ = self.pool1(x, edge_index, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x, edge_index, batch, _ = self.pool2(x, edge_index, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2
x = self.linear(x)
#x = torch.sigmoid(x)
x = x.squeeze(1)
return x
def forward(self, batched_data):
x, edge_index, edge_attr, node_depth, batch = batched_data.x, batched_data.edge_index, batched_data.edge_attr, batched_data.node_depth, batched_data.batch
x = self.node_encoder(x, node_depth.view(-1,))
xs = []
x = F.relu(self.conv1(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool1(x, edge_index, edge_attr, batch)
xs += [torch.cat([gmp(x, batch), gap(x, batch)], dim=1)]
for i in range(self.num_layers-1):
x = F.relu(self.convs[i](x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pools[i](x, edge_index, edge_attr, batch)
xs += [torch.cat([gmp(x, batch), gap(x, batch)], dim=1)]
x = xs[0]
for i in range(1, len(xs)):
x += xs[i]
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.relu(self.lin2(x))
pred_list = []
for i in range(self.max_seq_len):
pred_list.append(self.graph_pred_linear_list[i](x))
return pred_list
def forward(self, x, edge_index, batch):
# x, edge_index, batch = data.x, data.edge_index, data.batch
x = F.relu(self.conv1(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool1(x, edge_index, None, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool2(x, edge_index, None, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool3(x, edge_index, None, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv4(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool4(x, edge_index, None, batch)
x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv5(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool5(x, edge_index, None, batch)
x5 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3 + x4 + x5
x = F.relu(self.lin1(x))
x = F.dropout(x, p=0.5, training=self.training)
x = F.relu(self.lin2(x))
x = F.softmax(self.lin3(x), dim=-1)
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
x = F.relu(self.conv1(x, edge_index))
# x, edge_index, _, batch, _, _ = self.pool1(x, edge_index, None, batch)
# x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x1 = gmp(x, batch)
x = F.relu(self.conv2(x, edge_index))
# x, edge_index, _, batch, _, _ = self.pool2(x, edge_index, None, batch)
# x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x2 = gmp(x, batch)
x = F.relu(self.conv3(x, edge_index))
# x, edge_index, _, batch, _, _ = self.pool3(x, edge_index, None, batch)
# x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x3 = gmp(x, batch)
x = x1 + x2 + x3
# x = F.relu(self.lin1(x))
# x = F.dropout(x, p=0.5, training=self.training)
x = F.relu(self.lin2(x))
x = F.dropout(x, p=0.5, training=self.training)
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, data):
x, edge_index, edge_attr, batch = data.x, data.edge_index, data.edge_attr, data.batch
x = self.embedding_layer(x)
# edge_attr = self.embedding_layer(edge_attr)
x = F.relu(self.conv1(x, edge_index))
x_local = self.l1(x)
x, edge_index, edge_attr, batch, _, _ = self.pool1(x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool2(x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, edge_attr, batch, _, _ = self.pool3(x, edge_index, edge_attr, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv4(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool4(x, edge_index, edge_attr, batch)
x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
# x = x1 + x2 + x3 + x4
x_global = (x1 + x2 + x3 + x4)
x = torch.cat((x_local, x_global.repeat(x_local.shape[0], 1)), dim=1)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=0.3, training=self.training)
x = F.relu(self.lin2(x))
x = F.log_softmax(self.lin3(x), dim=-1)
# print (x.shape)
return x
def forward(self, x, edge_index, batch, edge_attr):
edge_attr = edge_attr.squeeze()
edge_index, edge_attr = self.augment_adj(edge_index, edge_attr,
x.size(0))
x = self.conv1(x, edge_index, edge_attr)
x, edge_index, edge_attr, batch, perm, score1 = self.pool1(
x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
edge_attr = edge_attr.squeeze()
edge_index, edge_attr = self.augment_adj(edge_index, edge_attr,
x.size(0))
x = self.conv2(x, edge_index, edge_attr)
x, edge_index, edge_attr, batch, perm, score2 = self.pool2(
x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = torch.cat([x1, x2], dim=1)
x = F.relu(self.bn4(self.fc1(x)))
x = F.dropout(x, p=0.5, training=self.training)
x = F.relu(self.bn5(self.fc2(x)))
x = F.dropout(x, p=0.5, training=self.training)
x = F.log_softmax(self.fc3(x), dim=-1)
return x, score1, score2
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
x = self.item_embedding(x)
x = x.squeeze(1)
x = F.relu(self.conv1(x, edge_index))
x, edge_index, _, batch, _ = self.pool1(x, edge_index, None, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x, edge_index, _, batch, _ = self.pool2(x, edge_index, None, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, _, batch, _ = self.pool3(x, edge_index, None, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3
x = self.lin1(x)
x = self.act1(x)
x = self.lin2(x)
x = self.act2(x)
x = F.dropout(x, p=0.5, training=self.training)
x = torch.sigmoid(self.lin3(x)).squeeze(1)
return x
def forward(self, data):
x, edge_index, edge_attr, batch = data.x, data.edge_index, data.edge_attr, data.batch
x = self.embedding_layer(x)
edge_attr = self.embedding_layer(edge_attr)
x = F.relu(self.conv1(x, edge_index, edge_weight=edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool1(
x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_weight=edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool2(
x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_weight=edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool3(
x, edge_index, edge_attr, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv4(x, edge_index, edge_weight=edge_attr))
x, edge_index, edge_attr, batch, _, _ = self.pool4(
x, edge_index, edge_attr, batch)
x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3 + x4
x = F.relu(self.lin1(x))
x = F.dropout(x, p=0.3, training=self.training)
x = F.relu(self.lin2(x))
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, data): x, edge_index, batch, weight = data.x, data.edge_index, data.batch, data.weight x = self.gbn1(F.relu(self.conv1(x, edge_index, weight))) x, edge_index, weight, batch, _, _ = self.pool1(x,edge_index,weight,batch) x1 = torch.cat([gmp(x,batch), gap(x,batch)],dim =1) x = self.gbn2(F.relu(self.conv2(x, edge_index, weight))) x, edge_index, weight, batch, _, _ = self.pool2(x, edge_index,weight, batch) x2 = torch.cat([gmp(x,batch), gap(x,batch)], dim=1) x = self.gbn3(F.relu(self.conv3(x, edge_index, weight))) x, edge_index, weight, batch, _, _ = self.pool3(x, edge_index,weight , batch) x3 = torch.cat([gmp(x,batch), gap(x,batch)], dim=1) x = self.gbn4(F.relu(self.conv3(x, edge_index, weight))) x, edge_index, _, batch, _, _ = self.pool4(x, edge_index,weight , batch) x4 = torch.cat([gmp(x,batch), gap(x,batch)], dim=1) x = torch.cat([x1, x2, x3, x4], dim=1) # x = self.set2set(x, batch) x = F.relu(self.lin1(x)) x = self.bn1(x) x = F.dropout(x, p=.2, training = self.training) x = F.relu(self.lin2(x)) x = self.bn2(x) #x = F.dropout(x, p=.5, training = self.training) x = self.lin3(x) return x.view(-1)
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
graph_feature = data.gf
x = F.relu(self.conv1(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool1(x, edge_index, None, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool2(x, edge_index, None, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index))
x, edge_index, _, batch, _, _ = self.pool3(x, edge_index, None, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = x1 + x2 + x3
x = torch.cat([x, graph_feature], dim=-1)
x = self.lin1(x)
x = activate_func(x, self.args["act"])
x = F.dropout(x, p=self.dropout, training=self.training)
x = self.lin2(x)
x = activate_func(x, self.args["act"])
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, batch):
x = batch.x
edge_index = batch.edge_index
batch_h = batch.batch
x = F.relu(self.conv_layer_1(x, edge_index))
x, edge_index, _, batch_h, _ = self.pool_layer_1(
x, edge_index, None, batch_h)
out = torch.cat([gmp(x, batch_h), gap(x, batch_h)], dim=1)
x = F.relu(self.conv_layer_2(x, edge_index))
x, edge_index, _, batch_h, _ = self.pool_layer_2(
x, edge_index, None, batch_h)
out += torch.cat([gmp(x, batch_h), gap(x, batch_h)], dim=1)
x = F.relu(self.conv_layer_3(x, edge_index))
x, edge_index, _, batch_h, _ = self.pool_layer_3(
x, edge_index, None, batch_h)
out += torch.cat([gmp(x, batch_h), gap(x, batch_h)], dim=1)
out = F.relu(self.lin_layer_1(out))
out = F.dropout(out, p=self.dropout, training=self.training)
out = F.relu(self.lin_layer_2(out))
out = F.log_softmax(self.lin_layer_3(out), dim=-1)
if batch.y is not None:
loss = F.nll_loss(out, batch.y)
return out, loss
return out, None
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
edge_attr = None
x = F.relu(self.conv1(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _ = self.pool1(x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _ = self.pool2(x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_attr))
x, edge_index, edge_attr, batch, _ = self.pool3(x, edge_index, edge_attr, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(x1) + F.relu(x2) + F.relu(x3)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.relu(self.lin2(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.log_softmax(self.lin3(x), dim=-1)
return x
def forward(self, data):
x, batch = data.x, data.batch
edge_index = knn_graph(x, 100, batch) #?
edge_index, _ = dropout_adj(edge_index, p=0.3) #?
batch = data.batch
x = F.leaky_relu(self.conv1(x, edge_index))
x1 = torch.cat([gap(x, batch), gmp(x, batch)], dim=1)
convlist = [x1]
for f in range(self.conv_depth - 1):
x = F.leaky_relu(self.convfkt[f](x, edge_index))
xi = torch.cat([gap(x, batch), gmp(x, batch)], dim=1)
convlist.append(xi)
x = torch.cat(convlist, dim=1)
x = self.batchnorm1(x)
for g in range(self.lin_depth):
x = F.leaky_relu(self.linearfkt[g](x))
if (
g - 1
) % 3 == 0 and self.lin_depth - 1 > g: #g=1,4,7,... u. noch mind. zwei weitere Layers
x = self.drop[g](x)
x = self.out(x)
if self.classification:
x = torch.sigmoid(x)
x = x.view(-1)
return x
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
edge_attr = None
if x is None:
x = torch.ones((batch.shape[0], 1)).to(device)
xs = []
batches = []
x = F.relu(self.conv1(x, edge_index, edge_attr))
xs.append(x)
batches.append(batch)
x, edge_index, edge_attr, batch = self.pool1(x, edge_index, edge_attr, batch)
xs.append(x)
batches.append(batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv2(x, edge_index, edge_attr))
xs.append(x)
batches.append(batch)
x, edge_index, edge_attr, batch = self.pool2(x, edge_index, edge_attr, batch)
xs.append(x)
batches.append(batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = F.relu(self.conv3(x, edge_index, edge_attr))
xs.append(x)
batches.append(batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
summary = F.relu(x1) + F.relu(x2) + F.relu(x3)
xs = [xs[i] for i in self.args.takeout]
batches = [batches[i] for i in self.args.takeout]
return summary, xs, batches
def forward(self, data):
x, edge_index, batch = data
edge_attr = None
edge_index = edge_index.transpose(0, 1)
x = self.relu(self.conv1(x, edge_index, edge_attr), negative_slope=0.1)
x, edge_index, edge_attr, batch, _, _ = self.pool1(
x, edge_index, None, batch)
# x, edge_index, edge_attr, batch, _ = self.pool1(x, edge_index, edge_attr, batch)
x1 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = self.relu(self.conv2(x, edge_index, edge_attr), negative_slope=0.1)
x, edge_index, edge_attr, batch, _, _ = self.pool2(
x, edge_index, None, batch)
# x, edge_index, edge_attr, batch, _ = self.pool2(x, edge_index, edge_attr, batch)
x2 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
#
x = self.relu(self.conv3(x, edge_index, edge_attr), negative_slope=0.1)
x, edge_index, edge_attr, batch, _, _ = self.pool3(
x, edge_index, None, batch)
# x, edge_index, edge_attr, batch, _ = self.pool2(x, edge_index, edge_attr, batch)
x3 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
# x = self.relu(self.conv4(x, edge_index, edge_attr), negative_slope=0.1)
# x, edge_index, edge_attr, batch, _, _ = self.pool4(x, edge_index, None, batch)
# x, edge_index, edge_attr, batch, _ = self.pool2(x, edge_index, edge_attr, batch)
# x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
# x = self.relu(self.conv5(x, edge_index, edge_attr),negative_slope=0.1)
# x, edge_index, edge_attr, batch, _, _ = self.pool5(x, edge_index, None, batch)
# x, edge_index, edge_attr, batch, _ = self.pool3(x, edge_index, edge_attr, batch)
x_information_score = self.calc_information_score(x, edge_index)
score = torch.sum(torch.abs(x_information_score), dim=1)
# x5 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
x = self.relu(x1, negative_slope=0.1) + self.relu(
x2, negative_slope=0.1) + self.relu(x3, negative_slope=0.1)
# x = self.relu(x1,negative_slope=0.1) + self.relu(x2,negative_slope=0.1)
# + self.relu(x3,negative_slope=0.1)+self.relu(x4,negative_slope=0.1)+self.relu(x5,negative_slope=0.1)
# x = F.relu(x1)
graph_emb = x
# x = self.lin1(x)
x = self.relu(self.lin1(x), negative_slope=0.1)
# x=self.bn1(x)
# x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = self.relu(self.lin2(x), negative_slope=0.1)
# x=self.bn2(x)
# x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = self.lin3(x)
# x = F.log_softmax(x, dim=-1)
return x, score.mean(), graph_emb
def forward(self, data, conv_train=False):
x = data.x
edge_index = data.edge_index
x1 = self.norm1(self.act1(self.conv1(x, edge_index)))
x = self.dropout(x1)
x2 = self.norm2(self.act2(self.conv2(x, edge_index)))
x = self.dropout(x2)
x3 = self.norm3(self.act3(self.conv3(x, edge_index)))
h_conv = torch.cat([x1, x2, x3], dim=1)
#compute GNN only output
conv_batch_avg = gap(h_conv, data.batch)
conv_batch_add = gadd(h_conv, data.batch)
conv_batch_max = gmp(h_conv, data.batch)
h_GNN = torch.cat([conv_batch_avg, conv_batch_add, conv_batch_max],
dim=1)
gnn_out = self.out_fun(self.lin_GNN(h_GNN))
if conv_train:
return None, None, gnn_out
#SOM
_, _, som_out_1 = self.som1(x1)
_, _, som_out_2 = self.som2(x2)
_, _, som_out_3 = self.som3(x3)
#READOUT
h1 = self.out_norm1(self.act1(self.out_conv1(som_out_1, edge_index)))
h2 = self.out_norm2(self.act2(self.out_conv2(som_out_2, edge_index)))
h3 = self.out_norm3(self.act3(self.out_conv3(som_out_3, edge_index)))
som_out_conv = torch.cat([h1, h2, h3], dim=1)
som_batch_avg = gap(som_out_conv, data.batch)
som_batch_add = gadd(som_out_conv, data.batch)
som_batch_max = gmp(som_out_conv, data.batch)
h = torch.cat([som_batch_avg, som_batch_add, som_batch_max], dim=1)
h = self.out_norm4(h)
h = self.out_act(self.lin_out1(h))
h = self.dropout(h)
h = self.out_act(self.lin_out2(h))
h = self.dropout(h)
h = self.out_fun(self.lin_out3(h))
return h, h_conv, gnn_out
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
x1 = F.relu(self.conv1(x, edge_index))
x2 = F.relu(self.conv2(x1, edge_index))
x2 = x1 + x2
x3 = F.relu(self.conv3(x2, edge_index))
x3 = x2 + x3
x = F.relu(self.conv4(x3, edge_index))
x, edge_index, _, batch, _ = self.pool1(x, edge_index, None, batch)
x4 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
#x4 = x3 + x4
x5 = F.relu(self.conv5(x, edge_index))
x5 = x + x5
x6 = F.relu(self.conv6(x5, edge_index))
x6 = x5 + x6
x7 = F.relu(self.conv7(x6, edge_index))
x7 = x6 + x7
x8 = F.relu(self.conv8(x7, edge_index))
x8 = x7 + x8
x = F.relu(self.conv9(x8, edge_index))
x, edge_index, _, batch, _ = self.pool2(x, edge_index, None, batch)
x9 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
#x9 = x8 + x9
x10 = F.relu(self.conv10(x, edge_index))
x10 = x + x10
x11 = F.relu(self.conv11(x10, edge_index))
x11 = x10 + x11
x12 = F.relu(self.conv12(x11, edge_index))
x12 = x11 + x12
x13 = F.relu(self.conv13(x12, edge_index))
x13 = x12 + x13
x = F.relu(self.conv14(x13, edge_index))
x, edge_index, _, batch, _ = self.pool3(x, edge_index, None, batch)
x14 = torch.cat([gmp(x, batch), gap(x, batch)], dim=1)
#x14 = x13 + x14
x = x4 + x9 + x14
x = F.relu(self.lin1(x))
x = F.dropout(x, p=self.dropout_ratio, training=self.training)
x = F.relu(self.lin2(x))
x = F.log_softmax(self.lin3(x), dim=-1)
return x
