Closed XuHan-CN closed 3 years ago
The MLP 13->32->128->64->1024 is the superedge filters-generating network. It creates a matrix F_ij 32x32 which encapsulate the nature of the adjacency between two neighboring superpoints. 13 is the number of superedge handcrafted features.
In ECC, the message sent by superpoint i to superpoint j is the hidden state h_i^t (size 32) multiplied by the corresponding superedge filters: F_ij x h_i (size 32)
Once all messages are sent, the incoming messages are averaged and this value (size 32) serves as input to the GRU to update the hidden state: h_i^{t+1} = GRU(hi^t, sum{j in N_i} F_ij h_j^t )
Finally, the hidden states are concatenate over the 10 message passing iteration (+ the initial one) into a 352=11×32 vector, to create class logits for the superpoint (13 classes here). Does this clear things up?
The following is the GraphConvModule