Graph Data Science

FastRP

A node embedding algorithm, short for Fast Random Projection. It builds each node's vector by combining random vectors drawn from the nodes around it.

Example

A vector of four numbers for each node in the projection.

cypher
CALL gds.fastRP.stream('people', {
  embeddingDimension: 4,
  randomSeed: 42
})
YIELD nodeId, embedding
RETURN gds.util.asNode(nodeId).name AS person, embedding

embeddingDimension sets how many numbers each vector holds. randomSeed fixes the random vectors the algorithm starts from, which would otherwise differ between runs.

Lessons that use this term

The lesson and course links below open in a new tab.

No published lesson uses this term yet.

All glossary terms