Deep Active Learning: Unified and Principled Method for Query and Training
share
In this paper, we proposed a unified and principled method for both querying and training process in deep batch active learning. We provided the theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameter and batch query selection through alternative optimization. In addition, the loss for training deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally we evaluated our proposed method for different benchmarks, showing consistently better empirical performances and more time efficient query strategy, comparing to several baselines.
READ FULL TEXT