Active Learning with Logged Data
This work addresses a specific problem in machine learning for researchers and practitioners dealing with biased data collection, though it appears incremental as it modifies existing methods.
The paper tackles the problem of active learning with logged data, where labeled examples are drawn from a logging policy, and aims to learn a classifier for the entire population. It proposes an algorithm that combines logged data with controlled experimentation, achieving improved performance by bootstrapping and informing experimentation.
We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior work addresses this problem either when only logged data is available, or purely in a controlled random experimentation setting where the logged data is ignored. In this work, we combine both approaches to provide an algorithm that uses logged data to bootstrap and inform experimentation, thus achieving the best of both worlds. Our work is inspired by a connection between controlled random experimentation and active learning, and modifies existing disagreement-based active learning algorithms to exploit logged data.