Package oracle.pgx.api.mllib

Class EdgeWiseModelBuilder<Model extends EdgeWiseModel,Config extends EdgeWiseModelConfig,Self extends EdgeWiseModelBuilder>

java.lang.Object

oracle.pgx.api.mllib.WiseModelBuilder<Config,Self>

oracle.pgx.api.mllib.EdgeWiseModelBuilder<Model,Config,Self>

Direct Known Subclasses:

SupervisedEdgeWiseModelBuilder, UnsupervisedEdgeWiseModelBuilder

public abstract class EdgeWiseModelBuilder<Model extends EdgeWiseModel,Config extends EdgeWiseModelConfig,Self extends EdgeWiseModelBuilder>
extends WiseModelBuilder<Config,Self>

Abstract builder class for EdgeWise models. Use SupervisedEdgeWiseModelBuilder instead of this.

Since:

23.1

Constructor Summary

Constructors

Constructor	Description
EdgeWiseModelBuilder()

Method Summary

Modifier and Type	Method	Description
abstract Model	build()	Builds the EdgeWise model with the specified parameters.
Self	setEdgeCombinationMethod(EdgeCombinationMethod edgeCombinationMethod)	Sets the edge embedding method for the algorithm.
Self	setTargetEdgeLabels(java.lang.String... targetEdgeLabels)	Set the target edge labels for the algorithm.
Self	setTargetEdgeLabels(java.util.List<java.lang.String> targetEdgeLabels)	Set the target edge labels for the algorithm.

Methods inherited from class oracle.pgx.api.mllib.WiseModelBuilder

setBatchSize, setConvLayerConfigs, setEdgeInputPropertyConfigs, setEdgeInputPropertyNames, setEdgeInputPropertyNames, setEmbeddingDim, setEnableAccelerator, setLearningRate, setNormalize, setNumEpochs, setSeed, setShuffle, setStandardize, setValidationConfig, setVertexInputPropertyConfigs, setVertexInputPropertyNames, setVertexInputPropertyNames, setWeightDecay

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

EdgeWiseModelBuilder

public EdgeWiseModelBuilder()

Method Detail

setTargetEdgeLabels

public Self setTargetEdgeLabels(java.util.List<java.lang.String> targetEdgeLabels)

Set the target edge labels for the algorithm. Only the related edges need to have the target property. Training and inference will be done on the edges with those labels

Parameters:

targetEdgeLabels - list of label names

Returns:

this

Since:

23.1

setTargetEdgeLabels

public Self setTargetEdgeLabels(java.lang.String... targetEdgeLabels)

Set the target edge labels for the algorithm. Only the related edges need to have the target property.

Parameters:

targetEdgeLabels - label names

Returns:

this

Since:

23.1

setEdgeCombinationMethod

public Self setEdgeCombinationMethod(EdgeCombinationMethod edgeCombinationMethod)

Sets the edge embedding method for the algorithm. See EdgeCombinationMethod

default: EdgeCombinationMethods.DEFAULT_CONCAT_METHOD

Parameters:

edgeCombinationMethod - edge embedding method

Returns:

this

Since:

23.1

build

public abstract Model build()
                     throws java.lang.InterruptedException,
                            java.util.concurrent.ExecutionException

Builds the EdgeWise model with the specified parameters.

Returns:

EdgeWise model

Throws:

java.lang.InterruptedException

java.util.concurrent.ExecutionException

Since:

23.1