difference between methods #22

Activity

1. AmirSh15

   changed the title [-]difference between models[/-] [+]difference between methods[/+] on Jul 11, 2019
2. RexYing commented on Aug 16, 2019

   

   RexYing

   on Aug 16, 2019

   Owner

   More actions

   Hi the soft-assign is the pooling method, base is the baseline, and set2set is the baseline with the set aggregation pooling for all node embeddings. The set2set method refers to "Order Matters: Sequence to sequence for sets"
3. RuihongQiu commented on Nov 26, 2019

   

   RuihongQiu

   on Nov 26, 2019

   More actions

   Hi the soft-assign is the pooling method, base is the baseline, and set2set is the baseline with the set aggregation pooling for all node embeddings. The set2set method refers to "Order Matters: Sequence to sequence for sets"

   Hi, I have a question of your implementation of Set2Set, which is come from the PyG issue.

   I am curious about the first computation step of the loop.

   hidden = (torch.zeros(self.num_layers, batch_size, self.lstm_output_dim).cuda(),
   	                  torch.zeros(self.num_layers, batch_size, self.lstm_output_dim).cuda())
   	
   q_star = torch.zeros(batch_size, 1, self.hidden_dim).cuda()
   for i in range(n):
       # q: batch_size x 1 x input_dim
       q, hidden = self.lstm(q_star, hidden)

   The input of the LSTM unit is q_star and hidden, which are initialized as 0 vectors. I am not sure if I am wrong that, the updated q and hidden in the first loop are only related to the initialized biases of the LSTM unit.