Federated learning (FL) has been intensively investigated in terms of
communication efficiency, privacy, and fairness. However, efficient annotation,
which is a pain point in real-world FL applications, is less studied. In this
project, we propose to apply active learning (AL) and sampling strategy into
the FL framework to reduce the annotation workload. We expect that the AL and
FL can improve the performance of each other complementarily. In our proposed
federated active learning (F-AL) method, the clients collaboratively implement
the AL to obtain the instances which are considered as informative to FL in a
distributed optimization manner. We compare the test accuracies of the global
FL models using the conventional random sampling strategy, client-level
separate AL (S-AL), and the proposed F-AL. We empirically demonstrate that the
F-AL outperforms baseline methods in image classification tasks.

研究通过在联邦学习框架中应用主动学习和采样策略来减少标注工作量，比较了全局 FL 模型使用传统随机采样策略、客户端级别分离的 AL（S-AL）和我们提出的 F-AL 的测试准确率，实验证明 F-AL 在图像分类任务中优于基线方法。