Modern Deep Neural Networks (DNNs) have achieved very high performance at the expense of computational resources. To decrease the computational burden, several techniques have proposed to extract, from a given DNN, efficient subnetworks which are able to preserve performance while reducing the number of network parameters. The literature provides a broad set of techniques to discover such subnetworks, but few works have studied the peculiar topologies of such pruned architectures. In this paper, we propose a novel \emph{unrolled input-aware} bipartite Graph Encoding (GE) that is able to generate, for each layer in an either sparse or dense neural network, its corresponding graph representation based on its relation with the input data. We also extend it into a multipartite GE, to capture the relation between layers. Then, we leverage on topological properties to study the difference between the existing pruning algorithms and algorithm categories, as well as the relation between topologies and performance.

翻译：现代深度神经网络（DNNs）以高昂的计算资源为代价实现了极高的性能。为降低计算负担，多项技术提出从给定的DNN中提取出能够保持性能同时减少网络参数数量的高效子网络。尽管已有大量文献提出多种发现此类子网络的技术，但针对此类剪枝架构独特拓扑结构的研究仍十分有限。本文提出一种新颖的输入感知展开二分图编码（GE），该编码能基于输入数据关系为稀疏或稠密神经网络的每一层生成对应的图表示。我们将其扩展为多部分图编码，以捕捉层间关系。进而利用拓扑特性研究现有剪枝算法及算法类别之间的差异，同时探究拓扑结构与性能之间的关联。