3 papers
cs.LG2026
Gradient-Discrepancy Acquisition for Pool-Based Active Learning
Mohamadsadegh Khosravani, Sandra Zilles
The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subs…
cs.LG2026
Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach
Mohamadsadegh Khosravani
We consider selective classification with abstention in the fixed-pool (or transductive) setting, where the unlabeled pool is given beforehand and only a subset of points can be qu…
cs.LG2022
Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning
Mohamadsadegh Khosravani, Sandra Zilles
The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness.…