Link Prediction

Cosine

single-GPU

cugraph.cosine(input_graph[, vertex_pair, ...])	Compute the Cosine similarity between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.
cugraph.link_prediction.cosine(input_graph)	Compute the Cosine similarity between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.

multi-GPU

Jaccard Coefficient

single-GPU

cugraph.jaccard(input_graph[, vertex_pair, ...])	Compute the Jaccard similarity between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.
cugraph.jaccard_coefficient(G[, ebunch])	For NetworkX Compatability.

multi-GPU

Overlap Coefficient

single-GPU

cugraph.overlap(input_graph[, vertex_pair, ...])	Compute the Overlap Coefficient between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.
cugraph.overlap_coefficient(G[, ebunch, ...])	Compute overlap coefficient.

multi-GPU

cugraph.dask.link_prediction.overlap.overlap(...)

Compute the Overlap Coefficient between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.

Sorensen Coefficient

single-GPU

cugraph.sorensen(input_graph[, vertex_pair, ...])	Compute the Sorensen coefficient between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.
cugraph.sorensen_coefficient(G[, ebunch])	Compute sorensen coefficient.

multi-GPU

cugraph.dask.link_prediction.sorensen.sorensen(...)

Compute the Sorensen coefficient between each pair of vertices connected by an edge, or between arbitrary pairs of vertices specified by the user.