Generative Adversarial Active Learning
This work addresses active learning for machine learning practitioners by introducing a novel method, though it appears incremental as it builds on existing uncertainty principles.
The paper tackles the problem of active learning by proposing a new query synthesis approach using Generative Adversarial Networks (GANs) to adaptively generate training instances, which in some settings outperforms traditional pool-based methods.
We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, this is the first active learning work using GAN.