Ein neuer Beitrag mit dem Titel "Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering" von Matthias Aßenmacher, Lukas Rauch, Jann Goschenhofer, Andreas Stephan, Bernd Bischl, Benjamin Roth und Bernhard Sick wurde auf dem "Workshop on Interactive Adapative Learning (IAL), ECML PKDD" vorgestellt. Der Beitrag beinhaltet Folgendes:

Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep
Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL
tackles the problem by adaptively posing the question of which data samples to annotate next in order
to achieve the best incremental learning improvement, although it suffers from several limitations that
hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed
to overcome these limitations and increase the practical applicability of DAL research. Specifically, we
discuss the opportunities to use the class discovery capabilities of CC and the possibility of further
reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL
algorithms will benefit from employing CC and WSL methods for the learning and labeling process.
We inspect the overlaps between the three research areas and identify relevant and exciting research
questions at the intersection of these areas.

Ein neuer Beitrag mit dem Titel "Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering" von Matthias Aßenmacher, Lukas Rauch, Jann Goschenhofer, Andreas Stephan, Bernd Bischl, Benjamin Roth und Bernhard Sick wurde auf dem "Workshop on Interactive Adapative Learning (IAL), ECML PKDD" vorgestellt. Der Beitrag beinhaltet Folgendes:

Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep
Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL
tackles the problem by adaptively posing the question of which data samples to annotate next in order
to achieve the best incremental learning improvement, although it suffers from several limitations that
hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed
to overcome these limitations and increase the practical applicability of DAL research. Specifically, we
discuss the opportunities to use the class discovery capabilities of CC and the possibility of further
reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL
algorithms will benefit from employing CC and WSL methods for the learning and labeling process.
We inspect the overlaps between the three research areas and identify relevant and exciting research
questions at the intersection of these areas.