
ITL proposes a novel approach to maximize information gain for specific prediction targets, outperforming state-of-the-art methods in various applications.


coremsg

information-based-transductive-active-learning-maximizing-information-gain-for-targeted-predictions


Information-based Transductive Active Learning: Maximizing Information Gain for Targeted Predictions


title_rewrite


The author proposes using bell curve sampling to enhance active learning efficiency by selecting instances from the uncertainty region most of the time without neglecting others, outperforming uncertainty sampling and passive learning in various datasets.


Improving-Active-Learning-with-Bell-Curve-Weight-Function


Improving Active Learning with Bell Curve Weight Function



The author argues that the decline in active learning performance using proxy-based methods stems from selecting redundant samples and compromising valuable pre-trained information. The proposed ASVP method aligns features and training to improve efficiency.


Efficient-Active-Learning-with-Proxy-Models-ASVP-Method


Efficient Active Learning with Proxy Models: ASVP Method
