Découvrir de nouvelles classes dans des données tabulaires
It addresses the lack of frameworks for novel class discovery in tabular data, a common but underexplored domain, though it appears incremental by extending existing NCD concepts to a new data type.
The paper tackles the problem of discovering new classes in heterogeneous tabular data, proposing TabularNCD, a method that extracts knowledge from known classes to guide discovery and shows NCD is applicable beyond images to tabular data.
In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes. While NCD has recently gained attention from the community, no framework has yet been proposed for heterogeneous tabular data, despite being a very common representation of data. In this paper, we propose TabularNCD, a new method for discovering novel classes in tabular data. We show a way to extract knowledge from already known classes to guide the discovery process of novel classes in the context of tabular data which contains heterogeneous variables. A part of this process is done by a new method for defining pseudo labels, and we follow recent findings in Multi-Task Learning to optimize a joint objective function. Our method demonstrates that NCD is not only applicable to images but also to heterogeneous tabular data.