Density Updater

Updates a density model. Note that the model can only be updated with the data it was initialized with in the corresponding initializer node ( Potential Density Initializer or Graph Density Initializer ). The update is performed by reducing the densities in the neighborhoods of all newly labeled data points according to the used density estimation algorithm.

Options

Unknown Row Handling

Depending on this setting, the node either ignores unknown rows (i.e. rows that were not used for the model creation) or fails if it encounters one.

Input Ports

Density scorer model created with either the Potential Density Initializer or the Graph Density Initializer node.

Table containing rows in whose neighborhoods the density in the model needs to be reduced. In an active learning setting these would be the rows that were freshly labeled by the user.

Output Ports

The updated model i.e. decreased densities in the neighborhood of rows in the input table.

Best Friends (Incoming)

• Graph Density Initializer (67 %) 
• Labeling View (33 %) 

Best Friends (Outgoing)

• Density Scorer (63 %) 
• Active Learning Loop End (38 %) 

Workflows

• 01_​Active_​Learning_​PBCA_​default (KNIME Hub) 
• 01_​Active_​Learning_​PBCA_​default (KNIME Hub) 
• 01_​Guided_​Labeling_​for_​Document_​Classification (KNIME Hub) 
• 02_​Active_​Learning_​for_​Document_​Classification (KNIME Hub) 
• 04_​Active_​Learning_​with_​basic_​SVM (KNIME Hub) 
• Show all 7 workflows

Installation

To use this node in KNIME, install KNIME Active Learning from the following update site:

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

You don't know what to do with this link? Read our NodePit Product and Node Installation Guide that explains you in detail how to install nodes to your KNIME Analytics Platform.

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.