[IGNITE-9587] [ML] Umbrella ticket: Handle different labels in training data and handle unknown labels in test or updated training data correctly

• Type: New Feature
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Ignite Flags: Docs Required
• Assignee: Alexey Zinoviev
• Reporter: Alexey Zinoviev
• Created: 13/Sep/18 15:44
• Updated: 13/Sep/18 15:44

Description

The problem is that all algorithms of binary classification are ready to handle the datasets marked with 0/1 labels and predict 0/1 labels without especial mapping.

Also the algorithms don't handle situation with unknown labels during the updating and testing phases

Possible solution: it could be stored in context of ML training