论文标题
控制分类器的方向正交
Controlling Directions Orthogonal to a Classifier
论文作者
论文摘要
我们建议确定给定分类器的方向不变，以便可以在样式转移等任务中控制这些方向。当给定的分类器是线性时，正交分解是直接识别的，但我们正式定义了非线性情况下正交性的概念。我们还提供了一种出乎意料的简单方法来构建正交分类器（使用给定分类器的分类器采用其他方向的分类器）。从经验上讲，我们介绍控制正交变化很重要的三种用例：样式转移，域的适应性和公平性。当域在多个方面变化时，正交分类器可实现所需的样式传输，通过标签移动来改善域的适应性，并减轻不公平作为预测指标。该代码可在http://github.com/newbeeer/orthogonal_classifier上找到
We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer. While orthogonal decomposition is directly identifiable when the given classifier is linear, we formally define a notion of orthogonality in the non-linear case. We also provide a surprisingly simple method for constructing the orthogonal classifier (a classifier utilizing directions other than those of the given classifier). Empirically, we present three use cases where controlling orthogonal variation is important: style transfer, domain adaptation, and fairness. The orthogonal classifier enables desired style transfer when domains vary in multiple aspects, improves domain adaptation with label shifts and mitigates the unfairness as a predictor. The code is available at http://github.com/Newbeeer/orthogonal_classifier
