Online probabilistic label trees
This addresses the need for efficient online learning algorithms in dynamic environments, but it appears incremental as it builds on existing label tree methods by adapting them to an online context.
The paper tackles the problem of training label tree classifiers in a fully online setting without prior knowledge, achieving low time and space complexity with strong theoretical guarantees. It demonstrates effectiveness in online multi-label and multi-class classification, including one- or few-shot learning scenarios, through a wide empirical study.
We introduce online probabilistic label trees (OPLTs), an algorithm that trains a label tree classifier in a fully online manner without any prior knowledge about the number of training instances, their features and labels. OPLTs are characterized by low time and space complexity as well as strong theoretical guarantees. They can be used for online multi-label and multi-class classification, including the very challenging scenarios of one- or few-shot learning. We demonstrate the attractiveness of OPLTs in a wide empirical study on several instances of the tasks mentioned above.