CheckBinaryVersion */

proto*/

proto*/

Wrapper for _build()

(A, B) * (C, D) = (A * C, A * D + B * C)

(A, B) * (C, D) = (A * C, A * D + B * C)

Helper function, assigns unique layer IDs.

if smoothing == 0, it's one-hot method if 0 < smoothing < 1, it's smooth method

Loads input data from gcn/data directory ind.dataset_str.x => the feature vectors and adjacency matrix of the training instances as list;

Loads input data from gcn/data directory ind.dataset_str.x => the feature vectors of the training instances as scipy.sparse.csr.csr_matrix o

Loads input data from gcn/data directory ind.dataset_str.x => the feature vectors of the training instances as scipy.sparse.csr.csr_matrix o

The constructed 'hamilton' W is a modified version of the quaternion representation, thus doing tf.matmul(Input,W) is equivalent to W * Inputs.

Accuracy with masking.

Softmax cross-entropy loss with masking.

Row-normalize sparse matrix

Parse index file.

Parse index file.

Preprocessing of adjacency matrix for simple GCN model and conversion to tuple representation.

Row-normalize feature matrix and convert to tuple representation

Row-normalize feature matrix