Home Multi-label classification
Post
Cancel

Multi-label classification

Multi-label classification

Main-references

  • [1] Comprehensive comparative study of multi-label classification methods

Problem description

A clear description of this problem is given in [1]:

In binary classification, the presence/absence of a single label is predicted. In MLC, the presence/absence of multiple labels is predicted and multiple labels can be assigned simultaneously to a sample. Most often, the MLC task is confused with multi-class classification (MCC). In MCC, there are also multiple classes (labels) that a given example can belong to, but a given example can belong to only one of these multiple classes. In that spirit, the MCC task can be seen as a special case of the MLC task, where exactly one label is relevant for each example.

This post is licensed under CC BY 4.0 by the author.