This node is currently not available in KNIME v5.9 — instead we’re showing this page for KNIME v5.1. You can use the version menu in the title bar to permanently switch your preferred version. This will also show the link to the update site.

GNN Heterogeneous Learner

Missing description.

Options

Hidden Channels: The number of hidden channels desired.
Hidden Layers: The number of hidden layers desired. Recommended to use a number less than the graph diameter if unsure.
Learning Rate: The learning rate to use in the optimizer
Epochs: The number of epochs to train for.

Input Ports

: Pickled Graph

Output Ports

: Pytorch Geometric Model
: Training Loss

Popular Predecessors

No recommendations found

Popular Successors

No recommendations found

Views

This node has no views

Workflows

No workflows found

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension GNN Extension from the below update site following our NodePit Product and Node Installation Guide:

v5.1

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 0.1.0.202406140144

On NodePit since: 2023-10-18

Last update: 2026-01-01

KNIME versions: From v5.1 to v5.1

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!