Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning
This provides a practical, efficient solution for machine learning practitioners, but it is incremental as it builds on existing single-point methods.
The paper tackles the problem of batch active learning by proposing a simple stochastic strategy that adapts single-point acquisition functions to batch settings, achieving performance comparable to state-of-the-art methods like BatchBALD or BADGE while using orders of magnitude less compute.
We examine a simple stochastic strategy for adapting well-known single-point acquisition functions to allow batch active learning. Unlike acquiring the top-K points from the pool set, score- or rank-based sampling takes into account that acquisition scores change as new data are acquired. This simple strategy for adapting standard single-sample acquisition strategies can even perform just as well as compute-intensive state-of-the-art batch acquisition functions, like BatchBALD or BADGE, while using orders of magnitude less compute. In addition to providing a practical option for machine learning practitioners, the surprising success of the proposed method in a wide range of experimental settings raises a difficult question for the field: when are these expensive batch acquisition methods pulling their weight?