State-Relabeling Adversarial Active Learning
This work addresses the challenge of reducing labeling costs in machine learning, though it appears incremental as it builds on existing adversarial active learning approaches.
The paper tackles the problem of label-efficient active learning by proposing a state relabeling adversarial active learning model (SRAAL) that selects informative unlabeled samples using annotation and state information, resulting in outperforming previous state-of-the-art methods on various datasets.
Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples. The SRAAL consists of a representation generator and a state discriminator. The generator uses the complementary annotation information with traditional reconstruction information to generate the unified representation of samples, which embeds the semantic into the whole data representation. Then, we design an online uncertainty indicator in the discriminator, which endues unlabeled samples with different importance. As a result, we can select the most informative samples based on the discriminator's predicted state. We also design an algorithm to initialize the labeled pool, which makes subsequent sampling more efficient. The experiments conducted on various datasets show that our model outperforms the previous state-of-art active learning methods and our initially sampling algorithm achieves better performance.