GraphSAGE supervised (AGA-only)
Preview

This algorithm is only available in Aura Graph Analytics.

Directed

Undirected

Heterogeneous nodes

Heterogeneous relationships

Weighted relationships

Node properties

Glossary

Directed: Directed trait. The algorithm is well-defined on a directed graph.
Directed: Directed trait. The algorithm ignores the direction of the graph.
Directed: Directed trait. The algorithm does not run on a directed graph.
Undirected: Undirected trait. The algorithm is well-defined on an undirected graph.
Undirected: Undirected trait. The algorithm ignores the undirectedness of the graph.
Heterogeneous nodes: Heterogeneous nodes fully supported. The algorithm has the ability to distinguish between nodes of different types.
Heterogeneous nodes: Heterogeneous nodes allowed. The algorithm treats all selected nodes similarly regardless of their label.
Heterogeneous relationships: Heterogeneous relationships fully supported. The algorithm has the ability to distinguish between relationships of different types.
Heterogeneous relationships: Heterogeneous relationships allowed. The algorithm treats all selected relationships similarly regardless of their type.
Weighted relationships: Weighted trait. The algorithm supports a relationship property to be used as weight, specified via the relationshipWeightProperty configuration parameter.
Weighted relationships: Weighted trait. The algorithm treats each relationship as equally important, discarding the value of any relationship weight.
Node properties: Node properties trait. The algorithm makes use of node properties.

Introduction

GraphSAGE is a graph neural network (GNN) architecture outlined in the paper Inductive Representation Learning on Large Graphs by Hamilton et al. (2017).

This section covers the syntax used to execute the GraphSAGE algorithm supervised to predict labels of nodes in a graph.

For node embeddings, see GraphSAGE unsupervised.

GraphSAGE supervised syntax per mode

Run GraphSAGE supervised in train mode on a named graph.

CALL gds.graphSage.supervised.train(
  graphName: String,
  configuration: Map
)
YIELD
  preProcessingMillis: Integer,
  trainMillis: Integer,
  configuration: Map

Table 1. Parameters
Name	Type	Default	Optional	Description
graphName	String	`n/a`	no	The name of a graph stored in the catalog.
configuration	Map	`{}`	yes	Configuration for algorithm-specifics and/or graph filtering.

Table 2. Configuration
Name	Type	Default	Optional	Description
activationFunction	String	`"relu"`	yes	The activation function to use. Valid values are "relu" and "sigmoid"
aggregator	String	`"mean"`	yes	The neighborhood embedding aggregator to use. Valid values are "mean" and "max"
batchSize	Integer	`n/a`	yes	The number of target nodes to train on in each batch. If not provided, the algorithm will automatically infer the maximally allowed batch size within the constraints of available memory
classWeights	Boolean	`false`	yes	Whether to use class weights to balance the training data. If set to true, class weights will be calculated based on the distribution of the target labels in the training set.
dropout	Float	`0.1`	yes	The dropout probability for each layer. Must be a value >= 0.0 and < 1.0
embeddingDimension	Integer	`256`	yes	The node embedding dimension of the model layers' outputs
epochs	Integer	`n/a`	no	The number of epochs to train the model
epochsPerVal	Integer	`0`	yes	The number of epochs between evaluating the model on the validation set. If set to 0, the model will not be evaluated on the validation set
featureProperties	List of String	`n/a`	no	The names of the node properties that should be used as input features. All property names must exist in the projected graph and be of type Float or List of Float.
jobId	String	`Generated internally`	yes	An ID that can be provided to more easily track the algorithm’s progress.
layerNormalization	Boolean	`true`	yes	Whether to apply layer normalization between the model layers
learningRate	Float	`0.001`	yes	The learning rate for the optimizer
modelName	String	`n/a`	no	The name of the model to train (must be unique)
nodeLabels	List of String	`["*"]`	yes	Filter the named graph using the given node labels.
numNeighbors	List	`[20, 10]`	yes	The number of neighbors to sample for each layer. Note that this also determines the number of layers
randomSeed	String	`n/a`	yes	A number used to seed all randomness of the computation
relationshipTypes	List of String	`["*"]`	yes	Filter the named graph using the given relationship types.
splitRatios	Map	`{"TRAIN" 0.6, "TEST" 0.2, "VALID" 0.2}`	yes	The ratios as a map to split the target nodes of the input graph into training, test, and validation sets. The keys must be "TRAIN", "TEST" and "VALID". The sum of the values must be 1.0
targetLabel	String	`n/a`	no	The node label (i.e. type) to train to predict on
targetProperty	String	`n/a`	no	The node property to train to predict, represented by a column in the input node table of the specified 'target_label'.

Table 3. Results
Name	Type	Description
preProcessingMillis	Integer	Milliseconds for preprocessing the graph.
trainMillis	Integer	Milliseconds to train the model.
configuration	Map	The configuration used for running the algorithm.

Run GraphSAGE supervised in stream mode on a named graph.

CALL gds.graphSage.supervised.stream(
  graphName: String,
  configuration: Map
)
YIELD
  nodeId: Integer,
  predictedClass: Integer,
  predictedProbabilities: List

Table 4. Parameters
Name	Type	Default	Optional	Description
graphName	String	`n/a`	no	The name of a graph stored in the catalog.
configuration	Map	`{}`	yes	Configuration for algorithm-specifics and/or graph filtering.

Table 5. Configuration
Name	Type	Default	Optional	Description
batchSize	Integer	`n/a`	yes	The number of nodes per batch.
featureProperties	List of String	`n/a`	no	The names of the node properties that should be used as input features. All property names must exist in the projected graph and be of type Float or List of Float.
jobId	String	`Generated internally`	yes	An ID that can be provided to more easily track the algorithm’s progress.
modelName	String	`n/a`	no	The name of a GraphSAGE supervised model in the model catalog.
nodeLabels	List of String	`["*"]`	yes	Filter the named graph using the given node labels. Nodes with any of the given labels will be included.
randomSeed	String	`n/a`	yes	A number used to seed all randomness of the computation
relationshipTypes	List of String	`["*"]`	yes	Filter the named graph using the given relationship types.

Table 6. Results
Name	Type	Description
nodeId	Integer	Node ID.
predictedClass	Integer	Predicted class for this node.
predictedProbabilities	List of Float	Probabilities for all classes, for this node.

Run GraphSAGE supervised in mutate mode on a graph stored in the catalog.

CALL gds.graphSage.supervised.mutate(
  graphName: String,
  configuration: Map
)
YIELD
  computeMillis: Integer,
  mutateMillis: Integer,
  nodePropertiesWritten: Integer,
  preProcessingMillis: Integer,
  configuration: Map

Table 7. Parameters
Name	Type	Default	Optional	Description
graphName	String	`n/a`	no	The name of a graph stored in the catalog.
configuration	Map	`{}`	yes	Configuration for algorithm-specifics and/or graph filtering.

Table 8. Configuration
Name	Type	Default	Optional	Description
batchSize	Integer	`n/a`	yes	The number of nodes per batch.
featureProperties	List of String	`n/a`	no	The names of the node properties that should be used as input features. All property names must exist in the projected graph and be of type Float or List of Float.
jobId	String	`Generated internally`	yes	An ID that can be provided to more easily track the algorithm’s progress.
modelName	String	`n/a`	no	The name of a GraphSAGE supervised model in the model catalog.
nodeLabels	List of String	`["*"]`	yes	Filter the named graph using the given node labels. Nodes with any of the given labels will be included.
randomSeed	String	`n/a`	yes	A number used to seed all randomness of the computation
relationshipTypes	List of String	`["*"]`	yes	Filter the named graph using the given relationship types.
mutateProperty	String	`n/a`	no	The node property in the GDS graph to which the embedding is written.
predictedProbabilityProperty	String	`n/a`	yes	The node property in which the class probability list is stored. If omitted, the probability list is discarded.

Table 9. Results
Name	Type	Description
computeMillis	Integer	Milliseconds for running the algorithm.
mutateMillis	Integer	Milliseconds for adding properties to the projected graph.
nodePropertiesWritten	Integer	Number of properties added to the projected graph.
preProcessingMillis	Integer	Milliseconds for preprocessing the graph.
configuration	Map	The configuration used for running the algorithm.

Run GraphSAGE supervised in write mode on a graph stored in the catalog.

CALL gds.graphSage.supervised.write(
  graphName: String,
  configuration: Map
)
YIELD
  computeMillis: Integer,
  nodePropertiesWritten: Integer,
  preProcessingMillis: Integer,
  writeMillis: Integer,
  configuration: Map

Table 10. Parameters
Name	Type	Default	Optional	Description
graphName	String	`n/a`	no	The name of a graph stored in the catalog.
configuration	Map	`{}`	yes	Configuration for algorithm-specifics and/or graph filtering.

Table 11. Configuration
Name	Type	Default	Optional	Description
batchSize	Integer	`n/a`	yes	The number of nodes per batch.
featureProperties	List of String	`n/a`	no	The names of the node properties that should be used as input features. All property names must exist in the projected graph and be of type Float or List of Float.
jobId	String	`Generated internally`	yes	An ID that can be provided to more easily track the algorithm’s progress.
modelName	String	`n/a`	no	The name of a GraphSAGE supervised model in the model catalog.
nodeLabels	List of String	`["*"]`	yes	Filter the named graph using the given node labels. Nodes with any of the given labels will be included.
randomSeed	String	`n/a`	yes	A number used to seed all randomness of the computation
relationshipTypes	List of String	`["*"]`	yes	Filter the named graph using the given relationship types.
predictedProbabilityProperty	String	`n/a`	yes	The node property in which the class probability list is stored. If omitted, the probability list is discarded.
writeConcurrency	String	`'concurrency'`	yes	The number of concurrent threads used for writing the node properties.
writeProperty	String	`n/a`	no	The node property in the Neo4j database to which the prediction is written

Table 12. Results
Name	Type	Description
computeMillis	Integer	Milliseconds for running the algorithm.
nodePropertiesWritten	Integer	Number of properties added to the projected graph.
preProcessingMillis	Integer	Milliseconds for preprocessing the graph.
writeMillis	Integer	Milliseconds for writing result data back.
configuration	Map	The configuration used for running the algorithm.

GraphSAGE supervised (AGA-only)Preview

Glossary

Introduction

GraphSAGE supervised (AGA-only)
Preview