15.3.3 Advanced Hyperparameter Customization
You can build an Unsupervised GraphWise model with only vertex properties or
only edge properties or both using rich hyperparameter customization.
This is implemented using the sub-config class,
GraphWiseConvLayerConfig
.
The following code
describes the implementation of the configuration in a Unsupervised GraphWise model.
The example also specifies a weight decay parameter of 0.001
and
dropout with dropping probability 0.5
for the model to counteract
overfitting.
opg4j> var weightProperty = analyst.pagerank(trainGraph).getName()
opg4j> var convLayerConfig = analyst.graphWiseConvLayerConfigBuilder().
setNumSampledNeighbors(25).
setActivationFunction(ActivationFunction.TANH).
setWeightInitScheme(WeightInitScheme.XAVIER).
setWeightedAggregationProperty(weightProperty).
setDropoutRate(0.5).
build()
opg4j> var dgiLayerConfig = analyst.graphWiseDgiLayerConfigBuilder().
setCorruptionFunction(new PermutationCorruption()).
setDiscriminator(GraphWiseDgiLayerConfig.Discriminator.BILINEAR).
setReadoutFunction(GraphWiseDgiLayerConfig.ReadoutFunction.MEAN).
build()
opg4j> var model = analyst.unsupervisedGraphWiseModelBuilder().
setVertexInputPropertyNames("vertex_features").
setEdgeInputPropertyNames("edge_features").
setConvLayerConfigs(convLayerConfig).
setDgiLayerConfig(dgiLayerConfig).
setLossFunction(UnsupervisedGraphWiseModelConfig.LossFunction.SIGMOID_CROSS_ENTROPY).
setEmbeddingDim(256).
setLearningRate(0.05).
setNumEpochs(30).
setSeed(42).
setShuffle(false).
setStandardize(true).
setBatchSize(64).
build()
String weightProperty = analyst.pagerank(trainGraph).getName();
GraphWiseConvLayerConfig convLayerConfig = analyst.graphWiseConvLayerConfigBuilder()
.setNumSampledNeighbors(25)
.setActivationFunction(ActivationFunction.TANH)
.setWeightInitScheme(WeightInitScheme.XAVIER)
.setWeightedAggregationProperty(weightProperty)
.setDropoutRate(0.5)
.build();
GraphWiseDgiLayerConfig dgiLayerConfig = analyst.graphWiseDgiLayerConfigBuilder()
.setCorruptionFunction(new PermutationCorruption())
.setDiscriminator(GraphWiseDgiLayerConfig.Discriminator.BILINEAR)
.setReadoutFunction(GraphWiseDgiLayerConfig.ReadoutFunction.MEAN)
.build();
UnsupervisedGraphWiseModel model = analyst.unsupervisedGraphWiseModelBuilder()
.setVertexInputPropertyNames("vertex_features")
.setEdgeInputPropertyNames("edge_features")
.setDgiLayerConfig(dgiLayerConfig)
.setLossFunction(UnsupervisedGraphWiseModelConfig.LossFunction.SIGMOID_CROSS_ENTROPY)
.setConvLayerConfigs(convLayerConfig)
.setWeightDecay(0.001)
.setEmbeddingDim(256)
.setLearningRate(0.05)
.setNumEpochs(30)
.setSeed(42)
.setShuffle(false)
.setStandardize(true)
.setBatchSize(64)
.build();
weightProperty = analyst.pagerank(train_graph).name
conv_layer_config = dict(num_sampled_neighbors=25,
activation_fn='tanh',
weight_init_scheme='xavier',
neighbor_weight_property_name=weightProperty,
dropout_rate=0.5)
conv_layer = analyst.graphwise_conv_layer_config(**conv_layer_config)
dgi_layer_config = dict(corruption_function=None,
readout_function="mean",
discriminator="bilinear")
dgi_layer = analyst.graphwise_dgi_layer_config(**dgi_layer_config)
params = dict(conv_layer_config=[conv_layer],
dgi_layer_config=dgi_layer,
loss_fn="sigmoid_cross_entropy",
vertex_input_property_names=["vertex_features"],
edge_input_property_names=["edge_features"],
weight_decay=0.001,
layer_size=256,
learning_rate=0.05,
num_epochs=30,
seed=42,
standardize=true,
batch_size=64
)
model = analyst.unsupervised_graphwise_builder(**params)
See UnsupervisedGraphWiseModelBuilder and GraphWiseConvLayerConfigBuilder in Javadoc for full description of all available hyperparameters and their default values.
Parent topic: Using the Unsupervised GraphWise Algorithm