用强化学习和图学习自动剪枝，让模型在边缘设备上更快更小。
AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
- 通过图结构建模网络拓扑，识别可剪枝的规律模式
- 实现最高90%剪枝率，FLOPs减少近18%
- 适合做模型压缩的工程师和研究者
随着深度神经网络（DNN）越来越多地部署在边缘设备上，针对有限计算资源优化模型至关重要。现有自动化剪枝方法受限于模型多样性、操作类型差异以及剪枝粒度与精度之间的平衡难题。为此，我们提出AutoSculpt，一种基于模式的自动化剪枝框架，结合图学习与深度强化学习（DRL），提升效率与精度。该框架包含三个关键步骤：(1) 将DNN构建为图以编码其拓扑结构与参数依赖关系；(2) 嵌入计算高效的剪枝模式；(3) 利用DRL迭代优化剪枝策略，直至压缩与精度达到最优平衡。实验结果表明，AutoSculpt在ResNet、MobileNet、VGG和Vision Transformer等多种架构上均表现优异，剪枝率最高达90%，FLOPs降低近18%，全面超越现有基线方法。
原文摘要 · Abstract (English)
As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face challenges due to the diversity of DNN models, various operators (e.g., filters), and the difficulty in balancing pruning granularity with model accuracy. To address these limitations, we introduce AutoSculpt, a pattern-based automated pruning framework designed to enhance efficiency and accuracy by leveraging graph learning and deep reinforcement learning (DRL). AutoSculpt automatically identifies and prunes regular patterns within DNN architectures that can be recognized by existing inference engines, enabling runtime acceleration. Three key steps in AutoSculpt include: (1) Constructing DNNs as graphs to encode their topology and parameter dependencies, (2) embedding computationally efficient pruning patterns, and (3) utilizing DRL to iteratively refine auto-pruning strategies until the optimal balance between compression and accuracy is achieved. Experimental results demonstrate the effectiveness of AutoSculpt across various architectures, including ResNet, MobileNet, VGG, and Vision Transformer, achieving pruning rates of up to 90% and nearly 18% improvement in FLOPs reduction, outperforming all baselines. The codes can be available at https://github.com/jlx15588/AutoSculpt
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。