发表机构
Intitute for Digital Technologies, Loughborough University London; Center for Neuromorphic Intelligence, Aston University（拉夫堡大学伦敦数字技术研究所; 阿斯顿大学神经形态智能中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ASF-S结构化剪枝框架，利用基于脑启发的PGI选择标准和AFC功能连接，实现70%参数缩减并无需重训练即可恢复基线准确率。
AI 中文摘要
结构化剪枝是一种模型压缩技术，用于降低在资源受限设备上部署深度神经网络的计算成本。流行的剪枝方法依赖于不透明的启发式方法或基于权重的标准，这些方法无法指示网络中的结构依赖关系。为了解决这些局限性，我们提出了人工结构功能搜索（ASF-S）：一种新颖的结构化剪枝框架。ASF-S利用主梯度重要性（PGI）：一种受大脑中结构-功能关系启发的新颖剪枝候选选择标准。通过确保模型的剪枝结构尊重输出层的拓扑组织，我们为人工神经网络定义了人工功能连接（AFC）。AFC提供的证据表明，通过仔细的剪枝候选选择标准，可以找到准确的小型网络。我们展示了PGI作为选择标准和ASF-S作为剪枝框架与近期基准测试的结果，证明我们的方法生成的模型变体参数减少70%，且无需重新训练剪枝层即可恢复基线准确率。
英文摘要
Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constrained devices. Popular methods of pruning rely on opaque heuristics or weight-based criteria that give no indication as to the structural dependencies in the network. To address these limitations we present Artificial Structure Function Search (ASF-S): a novel structured pruning framework. ASF-S utilizes Principle Gradient Importance (PGI): a novel prune-candidate selection criteria that is inspired by structure-function relationships in the brain. By ensuring the pruned structure of the model respects topographical organization of the output layer, we define Artificial Functional Connectivity (AFC) for artificial neural networks. AFC provides evidence to demonstrate that accurate smaller networks can be found using careful prune candidate selection criteria. We present results for PGI as a selection criterion and for ASF-S as a pruning framework against recent benchmarks, demonstrating that our method yields model variants with 70\% parameter reduction, that can recover baseline accuracy without re-training the pruned layers.
