Inplement in codes is different with paper, and I think it's not a graph convolution

[weizier]

What is implemented here is not a graph convolution, I think it's just a mapping with a matrix. And what confuses me most is that each node of the graph is not related to any other nodes in a sentence. Where am I wrong? Thanks a lot. And I also have a question: there is an adjacency matrix in the common GCN, but here there is not this matrix, instead, there is a mask, but what the mask does is just a 'multiply' operation element-wise not a matrix multiply in the common GCN. Any ideas? Thanks!