论文标题
通过最佳运输镜头重新审视全球汇集
Revisiting Global Pooling through the Lens of Optimal Transport
论文作者
论文摘要
全球合并是许多机器学习模型和任务中最重要的操作之一，但是在实践中，实施通常是经验的。在这项研究中，我们通过最佳运输镜头开发了一个新颖而坚实的全球合并框架。我们证明，大多数现有的全球合并方法等同于解决不平衡最佳运输（UOT）问题的一些专业。使UOT问题的参数可学习，我们在同一框架中统一了各种全局合并方法，因此，为神经网络提出了一个称为UOT-Pooling（UOTP）的广义全局池层。除了基于经典的Sinkhorn缩放算法实现UOTP层外，我们还基于Bregman ADMM算法设计了一种新的模型体系结构，该体系结构具有更好的数值稳定性，并且可以更有效地重现现有的池化层。我们在几种应用程序方案中测试了UOTP层，包括多构度学习，图形分类和图像分类。我们的UOTP层可以模仿常规的全球合并层，也可以学习一些新的合并机制，从而提高性能。
Global pooling is one of the most significant operations in many machine learning models and tasks, whose implementation, however, is often empirical in practice. In this study, we develop a novel and solid global pooling framework through the lens of optimal transport. We demonstrate that most existing global pooling methods are equivalent to solving some specializations of an unbalanced optimal transport (UOT) problem. Making the parameters of the UOT problem learnable, we unify various global pooling methods in the same framework, and accordingly, propose a generalized global pooling layer called UOT-Pooling (UOTP) for neural networks. Besides implementing the UOTP layer based on the classic Sinkhorn-scaling algorithm, we design a new model architecture based on the Bregman ADMM algorithm, which has better numerical stability and can reproduce existing pooling layers more effectively. We test our UOTP layers in several application scenarios, including multi-instance learning, graph classification, and image classification. Our UOTP layers can either imitate conventional global pooling layers or learn some new pooling mechanisms leading to better performance.
