Package oracle.pgx.api.mllib

Class SupervisedGnnExplainer

java.lang.Object

oracle.pgx.api.mllib.GnnExplainer

oracle.pgx.api.mllib.SupervisedGnnExplainer

public class SupervisedGnnExplainer
extends GnnExplainer

GnnExplainer object for SupervisedGraphWiseModel.

Since:

22.2

Method Summary

Modifier and Type	Method	Description
<ID> SupervisedGnnExplanation<ID>	inferAndExplain(PgxGraph graph, PgxVertex<ID> vertex)	Blocking version of inferAndExplainAsync(PgxGraph, PgxVertex).
<ID> SupervisedGnnExplanation<ID>	inferAndExplain(PgxGraph graph, PgxVertex<ID> vertex, float threshold)	Blocking version of inferAndExplainAsync(PgxGraph, PgxVertex, float).
<ID> PgxFuture<SupervisedGnnExplanation<ID>>	inferAndExplainAsync(PgxGraph graph, PgxVertex<ID> vertex)	Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.
<ID> PgxFuture<SupervisedGnnExplanation<ID>>	inferAndExplainAsync(PgxGraph graph, PgxVertex<ID> vertex, float threshold)	Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.
SupervisedGnnExplainer	learningRate(double learningRate)	Set the learning rate for the explainer.
SupervisedGnnExplainer	marginalize(boolean marginalize)	Set whether the explainer loss is marginalized over features.
SupervisedGnnExplainer	numOptimizationSteps(int numOptimizationSteps)	Set the number of optimization steps for the explainer.

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

learningRate, marginalize, numOptimizationSteps

Methods inherited from class java.lang.Object

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

Method Detail

inferAndExplainAsync

public <ID> PgxFuture<SupervisedGnnExplanation<ID>> inferAndExplainAsync(PgxGraph graph,
                                                                         PgxVertex<ID> vertex)

Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.

Parameters:

graph - the input graph

vertex - the vertex

Returns:

explanation containing feature importance and vertex importance.

Since:

22.2

inferAndExplainAsync

public <ID> PgxFuture<SupervisedGnnExplanation<ID>> inferAndExplainAsync(PgxGraph graph,
                                                                         PgxVertex<ID> vertex,
                                                                         float threshold)

Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.

Parameters:

graph - the input graph

vertex - the vertex

threshold - decision threshold

Returns:

explanation containing feature importance and vertex importance.

Since:

22.2

inferAndExplain

public <ID> SupervisedGnnExplanation<ID> inferAndExplain(PgxGraph graph,
                                                         PgxVertex<ID> vertex)

Blocking version of inferAndExplainAsync(PgxGraph, PgxVertex). Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.

Parameters:

graph - the input graph

vertex - the vertex

Returns:

explanation containing feature importance and vertex importance.

Since:

22.2

inferAndExplain

public <ID> SupervisedGnnExplanation<ID> inferAndExplain(PgxGraph graph,
                                                         PgxVertex<ID> vertex,
                                                         float threshold)

Blocking version of inferAndExplainAsync(PgxGraph, PgxVertex, float). Performs inference on the specified vertex and generates an explanation that contains scores of how important each property and each vertex in the computation graph is for the prediction.

Parameters:

graph - the input graph

vertex - the vertex

threshold - threshold

Returns:

explanation containing feature importance and vertex importance.

Since:

22.2

numOptimizationSteps

public SupervisedGnnExplainer numOptimizationSteps(int numOptimizationSteps)

Set the number of optimization steps for the explainer.

Parameters:

numOptimizationSteps - number of optimization steps

Since:

22.2

learningRate

public SupervisedGnnExplainer learningRate(double learningRate)

Set the learning rate for the explainer.

Parameters:

learningRate - learning rate

Since:

22.2

marginalize

public SupervisedGnnExplainer marginalize(boolean marginalize)

Set whether the explainer loss is marginalized over features. This can help in cases where there are important features that take values close to zero. Without marginalization the explainer can learn to mask such features out even if they are important, marginalization solves this by instead learning a mask for the deviation from the estimated input distribution.

Parameters:

marginalize - true if loss should be marginalized, false otherwise

Since:

22.2