Resize the memory space. Reallocate only if the capacity is not enough. */

Return information about the graph */

Reallocate the memory space */

Copy the memory space back from GPU */

load(**kwargs) Load a graph from file or Python object. Arguments depend on the underlying graph type.

Clear the graph and free CPU memory */

Divide a normal graph into a train split and several test splits for link prediction use. Each test split contains half true and half

Copy data from another memory */

Scatter data to a pool according to an index mapping */

Copy the memory space to GPU (asynchronous) */

Free CPU and GPU memory, except the embeddings on CPU */

build(**kwargs) Build the solver from the graph. Arguments depend on the underlying solver type.

Divide a graph into several splits. Parameters: graph_file (str): graph file files (list of str): file names

Gather data from a pool according to an index mapping. Automatically resize the memory when necessary. */

Swap two memory spaces */

Extract top-k labels. Parameters: label_file (str): label file save_file (str): save file k (int

train(**kwargs) Train embeddings with the solver. Arguments depend on the underlying solver type.

Construct a default optimizer */

* @brief Determine and allocate all resources for the solver * @param _graph graph * @param _optimizer optimizer or learning rate * @pa

Count edges for each sample block. This function can be parallelized. */

Convert ``csv`` to ``txt``. Parameters: csv_file: csv file txt_file: txt file

evaluate(task, **kwargs) Evaluate the learned embeddings on a downstream task. Arguments depend on the underlying graph type and the t

Load model in pickle format. Parameters: file_name (str): file name:

* @brief Predict logits for samples * @param _samples edge samples */

Save model in pickle format. Parameters: file_name (str): file name save_hyperparameter (bool, optional): sa

Set the format for parsing input data. Parameters: delimiters (str, optional): string of delimiter characters

Compute current learning rate according to the schedule */

Flatten the adjacency list to an edge list */

Compute feature vectors for an image dataset using a neural network. Parameters: dataset (torch.utils.data.Dataset): dat

Induce a subgraph from labeled nodes. All edges in the induced graph have at least one labeled node. Parameters: graph_f

Return information about the solver */

Sample edges. This function can be parallelized. */

Scatter data to a pool by substraction, according to an index mapping */

Visualize learned 2D or 3D coordinates. Parameters: Y (list of str, optional): labels of vectors file_name (

Construct a learning rate schedule */