Wrapper for tf.matmul (sparse vs dense).

Wrapper for _build()

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

Glorot & Bengio (AISTATS 2010) init.

Accuracy with masking.

Softmax cross-entropy loss with masking.

Create mask.

Dropout for sparse tensors.

Convert sparse matrix to tuple representation.

All zeros.

Construct feed dictionary.

Symmetrically normalize adjacency matrix.

Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices (tuple representation).

Helper function, assigns unique layer IDs.

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

Parse index file.

Row-normalize feature matrix and convert to tuple representation

Wrapper for _build()

All ones.

Uniform init.