AutoProtoNet: Interpretability for Prototypical Networks
AutoProtoNet: Interpretability for Prototypical Networks
复制标题
AutoProtoNet：原型网络的可解释性
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
W. Lawson
中科院分区：
文献类型：
--
作者：
Pedro Sandoval Segura;W. Lawson
在元学习方法中，从业者很难理解模型使用了哪种表示。如果没有这种能力，就很难理解模型知道什么，也很难做出有意义的修正。为了解决这些挑战，我们引入了AutoProtoNet，它通过训练一个适合重建输入的嵌入空间来构建原型网络的可解释性，同时保持对少量学习的便利。我们演示了如何将嵌入空间中的点可视化并用于理解类表示。我们还设计了一种原型改进方法，该方法允许人类调试不适当的分类参数。我们在一个自定义分类任务上使用这种调试技术，发现它可以提高由野外图像组成的验证集的准确性。我们提倡元学习方法的可解释性，并展示了人类增强元学习算法的交互式方法。
In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful corrections. To address these challenges, we introduce AutoProtoNet, which builds interpretability into Prototypical Networks by training an embedding space suitable for reconstructing inputs, while remaining convenient for few-shot learning. We demonstrate how points in this embedding space can be visualized and used to understand class representations. We also devise a prototype refinement method, which allows a human to debug inadequate classification parameters. We use this debugging technique on a custom classification task and find that it leads to accuracy improvements on a validation set consisting of in-the-wild images. We advocate for interpretability in meta-learning approaches and show that there are interactive ways for a human to enhance meta-learning algorithms.