论文标题
从层次结构到公平的基于原型的分类
Prototype Based Classification from Hierarchy to Fairness
论文作者
论文摘要
人工神经网可以代表和分类多种类型的数据，但通常是针对特定应用程序量身定制的，例如“公平”或“分层”分类。一旦选择了建筑，人类通常很难为新任务调整模型。例如，分层分类器不能轻易地转换为屏蔽受保护字段的公平分类器。我们在这项工作中的贡献是一种新的神经网络体系结构，即概念子空间网络（CSN），它概括了现有的专用分类器，以产生能够学习一系列多概念关系的统一模型。我们证明，在执行概念独立性时，CSN可以将最新的最新分类转换为层次结构分类器，甚至调和单个分类器中的公平和层次结构。 CSN的灵感来自现有的基于原型的分类器，这些分类器可促进可解释性。
Artificial neural nets can represent and classify many types of data but are often tailored to particular applications -- e.g., for "fair" or "hierarchical" classification. Once an architecture has been selected, it is often difficult for humans to adjust models for a new task; for example, a hierarchical classifier cannot be easily transformed into a fair classifier that shields a protected field. Our contribution in this work is a new neural network architecture, the concept subspace network (CSN), which generalizes existing specialized classifiers to produce a unified model capable of learning a spectrum of multi-concept relationships. We demonstrate that CSNs reproduce state-of-the-art results in fair classification when enforcing concept independence, may be transformed into hierarchical classifiers, or even reconcile fairness and hierarchy within a single classifier. The CSN is inspired by existing prototype-based classifiers that promote interpretability.
