.png){kind=icon}
Return
Exploratory machine learning with unknown unknowns
.png){kind=icon}
OA
AI
DOI：10.1016/j.artint.2023.104059.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In conventional supervised learning, a training dataset is given with ground -truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there are unknown classes in the training data misperceived as other labels, and thus their existence appears unknown from the given supervision. We attribute the unknown unknowns to the fact that the training dataset is badly advised by the incompletely perceived label space due to the insufficient feature information. To this end, we propose the exploratory machine learning, which examines and investigates training data by actively augmenting the feature space to discover potentially hidden classes. Our method consists of three ingredients including rejection model, feature exploration, and model cascade. We provide theoretical analysis to justify its superiority, and validate the effectiveness on both synthetic and real datasets.
Keywords:
Exploratory machine learning
Unknown unknowns
Robust AI
Robustness
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.9
Papers:
6.1K
Citations:
1.9W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
ShareSave
View more