We generalize active learning to address real-world settings where sampling
is restricted to an accessible region of the domain, while prediction targets
may lie outside this region. To this end, we propose ITL, short for
information-based transductive learning, an approach which samples adaptively
to maximize the information gained about specified prediction targets. We show,
under general regularity assumptions, that ITL converges uniformly to the
smallest possible uncertainty obtainable from the accessible data. We
demonstrate ITL in two key applications: Few-shot fine-tuning of large neural
networks and safe Bayesian optimization, and in both cases, ITL significantly
outperforms the state-of-the-art.

我们将主动学习推广到应对真实世界中的情况，其中采样被限制在域的可访问区域内，而预测目标可能位于该区域之外。为此，我们提出了 ITL，即信息驱动的转导学习，一种自适应采样的方法，旨在最大限度地提高对指定预测目标的信息获取。在普遍的规则性假设下，我们证明 ITL 会一致地收敛到可从可访问数据中获得的最小不确定性。我们在两个关键应用中展示了 ITL 的应用：大型神经网络的少样本微调和安全贝叶斯优化，ITL 在这两种情况下明显优于现有技术。

基于信息的迁移式主动学习

Information-based Transductive Active Learning

We study the active few-shot fine-tuning of large neural networks to
downstream tasks. We show that few-shot fine-tuning is an instance of a
generalization of classical active learning, transductive active learning, and
we propose ITL, short for information-based transductive learning, an approach
which samples adaptively to maximize the information gained about specified
downstream tasks. Under general regularity assumptions, we prove that ITL
converges uniformly to the smallest possible uncertainty obtainable from the
accessible data. To the best of our knowledge, we are the first to derive
generalization bounds of this kind, and they may be of independent interest for
active learning. We apply ITL to the few-shot fine-tuning of large neural
networks and show that ITL substantially improves upon the state-of-the-art.

我们研究了大型神经网络在下游任务中的主动少样本微调问题。我们证明了少样本微调是传统主动学习、转导式主动学习的一种泛化，并提出了信息导向的转导学习（ITL）方法，该方法通过适应性采样来最大化对指定下游任务的信息获取。在一般正则性假设下，我们证明了 ITL 收敛于可从可访问数据中获得的最小不确定性。据我们所知，我们是第一个推导出这种泛化界限的研究者，这对于主动学习可能具有独立的利益。我们将 ITL 应用于大型神经网络的少样本微调，并展示 ITL 相比现有技术取得了显著改进。