InitializeGraphLearningModel: Find edges that share nodes and add them to a data frame.

In ncats/MultiOmicsGraphPrediction: Network-Based Ensemble Prediction from IntLIM Predictors

Find edges that share nodes and add them to a data frame.

Description

Find edges that share nodes and add them to a data frame.

Usage

InitializeGraphLearningModel(
  modelInputs,
  iterations = 1000,
  convergenceCutoff = 0.001,
  learningRate = 0.2,
  optimizationType = "SGD",
  initialMetaFeatureWeights = 0
)

Arguments

modelInputs	An object of the ModelInput class.
iterations	Maximum number of iterations. Default is 1,000.
convergenceCutoff	Cutoff for convergence. Default is 0.001.
learningRate	Learning rate to use during training. Default is 0.2
optimizationType	Type of optimization. May be "SGD", "momentum", "adagrad", or "adam". Default is "SGD".
initialMetaFeatureWeights	Initial weights for model meta-features. Default is 0, which results in each meta-feature being given equal weight.

Value

An object of the ModelResults class. This object will later be filled in with the weights and errors from each iteration as well as the initial settings and data and the final result.

ncats/MultiOmicsGraphPrediction documentation built on Aug. 23, 2023, 9:19 a.m.