Class UnsupervisedGraphWiseModel

java.lang.Object

oracle.pgx.api.mllib.Model<UnsupervisedGraphWiseModel>

oracle.pgx.api.mllib.GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

oracle.pgx.api.mllib.UnsupervisedGraphWiseModel

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

UnsupervisedAnomalyDetectionGraphWiseModel

public class UnsupervisedGraphWiseModel
extends GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

A variant of Deep Graph Infomax (DGI). See UnsupervisedGraphWiseModelBuilder for documentation of the hyperparameters.

Since:

21.2

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	UnsupervisedGraphWiseModel.UnsupervisedGraphWiseInferenceType

Field Summary

Fields

Modifier and Type	Field	Description
static final String	ALGORITHM_NAME

Constructor Summary

Constructors

Constructor	Description
UnsupervisedGraphWiseModel(PgxSession session, oracle.pgx.api.internal.Core core, Supplier<String> keystorePathSupplier, Supplier<char[]> keystorePasswordSupplier, oracle.pgx.api.internal.mllib.ModelMetadata modelMetadata, BiFunction<PgxSession, oracle.pgx.api.internal.Graph, PgxGraph> graphConstructor)
UnsupervisedGraphWiseModel(PgxSession session, oracle.pgx.api.internal.Core core, Supplier<String> keystorePathSupplier, Supplier<char[]> keystorePasswordSupplier, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata modelMetadata, BiFunction<PgxSession, oracle.pgx.api.internal.Graph, PgxGraph> graphConstructor)	This constructor should never be used to get a model.

Method Summary

Modifier and Type	Method	Description
PgxFuture<Double>	fitAsync(PgxGraph graph)	Trains the GraphWise model on the input graph.
PgxFuture<Double>	fitAsync(PgxGraph trainGraph, PgxGraph valGraph)	Trains the GraphWise model on the input graph.
GraphWiseEmbeddingConfig	getEmbeddingConfig()	Gets the configuration object for the embedding method
UnsupervisedGraphWiseModelConfig.LossFunction	getLossFunction()	Gets the loss function
PgxFuture<PgxFrame>	getTrainingLogAsync()	Gets the training log that has evaluation results from validation.
UnsupervisedGnnExplainer	gnnExplainer()	Get a GnnExplainer object that can explain this model's predictions.
<ID> PgxFuture<PgxFrame>	inferEmbeddingsAsync(PgxGraph graph, Iterable<PgxVertex<ID>> vertices)	Infers the embeddings for the specified vertices.
void	store(String path, String key)	Blocking version of storeAsync(String, String).
void	store(String path, String key, boolean overwrite)	Blocking version of storeAsync(String, String).
PgxFuture<Void>	storeAsync(String path, String key)	Stores the GraphWise model in the specified path, with encryption.
PgxFuture<Void>	storeAsync(String path, String key, boolean overwrite)	Stores the GraphWise model in the specified path, with encryption.

Methods inherited from class GraphWiseModel

destroy, destroyAsync, fit, fit, getBatchSize, getConfig, getConvLayerConfigs, getEdgeInputFeatureDim, getEdgeInputPropertyNames, getEmbeddingDim, getInputFeatureDim, getLearningRate, getNumEpochs, getSeed, getTrainingLog, getTrainingLoss, getVertexInputPropertyNames, inferEmbeddings, isFitted

Methods inherited from class Model

close, export

Methods inherited from class Object

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

Field Details

ALGORITHM_NAME

public static final String ALGORITHM_NAME

See Also:

• Constant Field Values

Constructor Details

UnsupervisedGraphWiseModel

public UnsupervisedGraphWiseModel(PgxSession session,
 oracle.pgx.api.internal.Core core,
 Supplier<String> keystorePathSupplier,
 Supplier<char[]> keystorePasswordSupplier,
 oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata modelMetadata,
 BiFunction<PgxSession, oracle.pgx.api.internal.Graph, PgxGraph> graphConstructor)

This constructor should never be used to get a model. Use UnsupervisedGraphWiseModelBuilder instead.

Parameters:

session - PgxSession to which the model is connected

core - Core to which the model is connected

modelMetadata - Metadata concerning the different hyper-parameters of the GraphWise Model

Since:

21.2

UnsupervisedGraphWiseModel

public UnsupervisedGraphWiseModel(PgxSession session,
 oracle.pgx.api.internal.Core core,
 Supplier<String> keystorePathSupplier,
 Supplier<char[]> keystorePasswordSupplier,
 oracle.pgx.api.internal.mllib.ModelMetadata modelMetadata,
 BiFunction<PgxSession, oracle.pgx.api.internal.Graph, PgxGraph> graphConstructor)

Method Details

fitAsync

public PgxFuture<Double> fitAsync(PgxGraph graph)

Trains the GraphWise model on the input graph.

Specified by:

fitAsync in class GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

Parameters:

graph - input graph to fit on.

Since:

21.2

fitAsync

public PgxFuture<Double> fitAsync(PgxGraph trainGraph,
 PgxGraph valGraph)

Trains the GraphWise model on the input graph.

Specified by:

fitAsync in class GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

Parameters:

trainGraph - input train graph to fit on.

valGraph - input graph to evaluate on for validation.

Since:

24.2

getTrainingLogAsync

public PgxFuture<PgxFrame> getTrainingLogAsync()

Gets the training log that has evaluation results from validation. It is available only after the model was trained with validation.

Specified by:

getTrainingLogAsync in class GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

Returns:

training log

Since:

24.2

inferEmbeddingsAsync

public <ID> PgxFuture<PgxFrame> inferEmbeddingsAsync(PgxGraph graph,
 Iterable<PgxVertex<ID>> vertices)

Infers the embeddings for the specified vertices.

Specified by:

inferEmbeddingsAsync in class GraphWiseModel<UnsupervisedGraphWiseModelConfig, oracle.pgx.api.internal.mllib.UnsupervisedGraphWiseModelMetadata, UnsupervisedGraphWiseModel>

Returns:

PgxFrame containing the embeddings for each vertex.

Since:

21.2

gnnExplainer

public UnsupervisedGnnExplainer gnnExplainer()

Get a GnnExplainer object that can explain this model's predictions.

Returns:

UnsupervisedGnnExplainer object

Since:

22.2

storeAsync

public PgxFuture<Void> storeAsync(String path,
 String key)
                           throws ExecutionException,
InterruptedException

Stores the GraphWise model in the specified path, with encryption.

Parameters:

path - path to store the model

key - the encryption key, or null if no encryption should be used.

Throws:

ExecutionException

InterruptedException

Since:

21.2

storeAsync

public PgxFuture<Void> storeAsync(String path,
 String key,
 boolean overwrite)

Stores the GraphWise model in the specified path, with encryption.

Parameters:

path - path to store the model

key - the encryption key, or null if no encryption should be used.

Since:

21.2

store

public void store(String path,
 String key)
           throws ExecutionException,
InterruptedException

Blocking version of storeAsync(String, String). Calls storeAsync(String, String) and waits for the returned PgxFuture to complete.

Throws:

InterruptedException - if the caller thread gets interrupted while waiting for completion.

ExecutionException - if any exception occurred during asynchronous execution. The actual exception will be nested.

Since:

21.2

store

public void store(String path,
 String key,
 boolean overwrite)
           throws ExecutionException,
InterruptedException

Blocking version of storeAsync(String, String). Calls storeAsync(String, String) and waits for the returned PgxFuture to complete.

Throws:

InterruptedException - if the caller thread gets interrupted while waiting for completion.

ExecutionException - if any exception occurred during asynchronous execution. The actual exception will be nested.

Since:

21.2

getLossFunction

public UnsupervisedGraphWiseModelConfig.LossFunction getLossFunction()

Gets the loss function

Returns:

loss function

Since:

21.2

getEmbeddingConfig

public GraphWiseEmbeddingConfig getEmbeddingConfig()

Gets the configuration object for the embedding method

Returns:

configuration

Since:

23.2