CIntToPy */

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

Convert sparse matrix to tuple representation.

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

RaiseArgTupleInvalid */

GetBuiltinName */

CIntFromPy */

Glorot & Bengio (AISTATS 2010) init.

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

ParseKeywords */

CIntToPy */

CIntToPy */

Wrapper for tf.matmul (sparse vs dense).

Symmetrically normalize adjacency matrix.

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

Row-normalize feature matrix and convert to tuple representation

Create mask.

Create mask.

Convert sparse matrix to tuple representation.

__GNUC__ */

SetupReduce */

CodeObjectCache */

Construct feed dictionary.

dataset: name of dataset test_proportion: ratio of test train split seed: random seed for random splitting of dataset

dataset: name of dataset test_proportion: ratio of test train split seed: random seed for random splitting of dataset

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

Symmetrically normalize adjacency matrix.

Symmetrically normalize adjacency matrix.

InitStrings */

RaiseDoubleKeywords */

RaiseNeedMoreValuesToUnpack */

RaiseNoneIterError */

RaiseTooManyValuesToUnpack */

ExtTypeTest */