kumoai.trainer.GNNModelPlan

Contents

kumoai.trainer.GNNModelPlan#

class kumoai.trainer.GNNModelPlan[source]#

Configuration parameters that define how the Kumo graph neural network is architected.

Variables:

  • channels – (list[int]) A list of potential dimension of layers in the Message Passing model (default: [64, 128, 256]). Supported Task Types: All

  • aggregation – (list[list["sum" | "mean" | "min" | "max" | "std"]]) A nested list of aggregation operators in the graph neural network aggregation process (default: [ ["sum", "mean", "max"], ["sum", "mean", "min", "max", "std"]]). Supported Task Types: All

Contents