Advocacy Learning：通过竞争和类条件表征学习
Advocacy Learning: Learning through Competition and Class-Conditional Representations
摘要：
我们介绍倡导学习，一种新的监督训练计划的注意力为基础的分类问题。倡导学习依赖于一个由两个连接的网络组成的框架：1）$N$倡导者（每个类一个），每个倡导者以注意力地图的形式输出一个参数，2）一个法官，根据这些参数预测类标签。每个倡导者产生一个类条件表示，其目标是说服法官，输入的例子属于他们的类，即使输入属于不同的类。应用于几个不同的分类任务，我们表明，倡导学习可以导致分类精度在相同的监督基线小的改进。通过一系列的后续实验，我们分析了这种类条件表征何时以及如何提高区分性能。虽然有点违反直觉，但一个框架，其中子网络被训练以竞争性地提供支持其类的证据，在许多情况下表现与标准学习方法相当。这为进一步探索监督学习中的竞争和类条件表示提供了基础。
英文摘要：
We introduce advocacy learning, a novel supervised training scheme for attention-based classification problems. Advocacy learning relies on a framework consisting of two connected networks: 1) $N$ Advocates (one for each class), each of which outputs an argument in the form of an attention map over the input, and 2) a Judge, which predicts the class label based on these arguments. Each Advocate produces a class-conditional representation with the goal of convincing the Judge that the input example belongs to their class, even when the input belongs to a different class. Applied to several different classification tasks, we show that advocacy learning can lead to small improvements in classification accuracy over an identical supervised baseline. Though a series of follow-up experiments, we analyze when and how such class-conditional representations improve discriminative performance. Though somewhat counter-intuitive, a framework in which subnetworks are trained to competitively provide evidence in support of their class shows promise, in many cases performing on par with standard learning approaches. This provides a foundation for further exploration into competition and class-conditional representations in supervised learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
