论文标题
部分可观测时空混沌系统的无模型预测
Absolute Zero-Shot Learning
论文作者
论文摘要
考虑到对数据版权和隐私问题的越来越多的担忧，我们提出了一种新颖的绝对零照片学习（AZSL）范式，即培训具有零实际数据的分类器。关键的创新是将教师模型作为数据保护，以指导AZSL模型培训而不会泄漏数据。 AZSL模型由生成器和学生网络组成，该网络可以在保持教师网络的性能的同时实现无日期知识转移。我们将AZSL任务中的“ Black-Box”和“ White-Box”方案研究为不同的模型安全级别。此外，我们还提供了在归纳和跨性环境中的教师模型的讨论。尽管令人尴尬的简单实现和数据失调的缺点，但我们的AZSL框架仍可以在“白色盒子”方案下保留最先进的ZSL和GZSL性能。广泛的定性和定量分析也证明了在“黑色框”方案下部署模型时的有希望的结果。
Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i.e., training a classifier with zero real data. The key innovation is to involve a teacher model as the data safeguard to guide the AZSL model training without data leaking. The AZSL model consists of a generator and student network, which can achieve date-free knowledge transfer while maintaining the performance of the teacher network. We investigate `black-box' and `white-box' scenarios in AZSL task as different levels of model security. Besides, we also provide discussion of teacher model in both inductive and transductive settings. Despite embarrassingly simple implementations and data-missing disadvantages, our AZSL framework can retain state-of-the-art ZSL and GZSL performance under the `white-box' scenario. Extensive qualitative and quantitative analysis also demonstrates promising results when deploying the model under `black-box' scenario.
