Network morphism is an effective learning scheme to morph a well-trained neural network to a new one with the network function completely preserved. However, existing network morphism scheme addresses only basic morphing types on the layer level. In this research, we address the central problem of network morphism at a higher level, i.e., how a convolutional layer can be morphed into an arbitrary module of a neural network. To simplify the representation of a network, we abstract a module as a graph with blobs as vertices and convolutional layers as edges. Based on this graph, the morphing process can be formulated as a graph transformation problem. Two atomic morphing operations are introduced to construct the graphs, based on which modules are classified into two families, i.e., simple morphable modules and complex modules. We present practical morphing solutions for both families, and prove that any module can be morphed from a single convolutional layer. Extensive experiments have been conducted based on the state-of-the-art ResNet on benchmarks to verify the effectiveness of the proposed solution.

中文翻译：

---

深度卷积神经网络的模块化变形：图方法

网络态射是一种有效的学习方案，可以将训练有素的神经网络变形为完全保留网络功能的新网络。然而，现有的网络态射方案仅解决层级上的基本变形类型。在这项研究中，我们在更高层次上解决了网络态射的核心问题，即如何将卷积层变形为神经网络的任意模块。为了简化网络的表示，我们将一个模块抽象为一个图，以斑点为顶点，卷积层为边。基于这个图，变形过程可以被表述为一个图转换问题。引入了两个原子变形操作来构造图，基于这些模块将模块分为两类，即简单的可变形模块和复杂模块。我们为这两个系列提供了实用的变形解决方案，并证明任何模块都可以从单个卷积层变形。基于最先进的 ResNet 在基准上进行了广泛的实验，以验证所提出的解决方案的有效性。