Existing neural active learning algorithms have aimed to optimize the predictive performance of neural networks (NNs) by selecting data for labelling. However, other than a good predictive performance, being robust against random parameter initializations is also a crucial requirement in safety-critical applications. To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness. Importantly, our EV-GP criterion is training-free, i.e., it does not require any training of the NN during data selection, which makes it computationally efficient. We empirically demonstrate that our EV-GP criterion is highly correlated with both initialization robustness and generalization performance, and show that it consistently outperforms baseline methods in terms of both desiderata, especially in situations with limited initial data or large batch sizes.

翻译：现有神经主动学习算法通过选择需标注的数据，旨在优化神经网络（NN）的预测性能。然而，在安全关键应用中，除了良好的预测性能外，对随机参数初始化的鲁棒性也是一项关键要求。为此，我们提出基于高斯过程的期望方差（EV-GP）准则，该准则在理论上保证所选数据点能够训练出同时具备（a）良好预测性能与（b）初始化鲁棒性的神经网络。重要的是，EV-GP准则无需训练，即在数据选择过程中无需对神经网络进行任何训练，从而具有计算高效性。实验表明，EV-GP准则与初始化鲁棒性和泛化性能高度相关，并在两种期望目标上持续优于基线方法，尤其是在初始数据有限或大批量场景下。