# Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment

arXiv: https://arxiv.org/abs/2403.19490 · HTML: https://mlsanity.com/paper/2403.19490/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 102 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)

## Built on by (most cited first, 9 of 9)

- [SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models](https://mlsanity.com/paper/2410.14720/) (2024)
- [Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2406.12042/) (2024)
- [Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection](https://mlsanity.com/paper/2409.15557/) (2024)
- [Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance](https://mlsanity.com/paper/2410.16151/) (2024)
- [LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation](https://mlsanity.com/paper/2507.21573/) (2025)
- [Dual sparse training framework: inducing activation map sparsity via Transformed ℓ1 regularization](https://mlsanity.com/paper/2405.19652/) (2024)
- [Layer Pruning with Consensus: A Triple-Win Solution](https://mlsanity.com/paper/2411.14345/) (2024)
- [Pruning Everything, Everywhere, All at Once](https://mlsanity.com/paper/2506.04513/) (2025)
- [SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning](https://mlsanity.com/paper/2507.02945/) (2025)

## Abstract (arXiv)

Structural model pruning is a prominent approach used for reducing the computational cost of Convolutional Neural Networks (CNNs) before their deployment on resource-constrained devices. Yet, the majority of proposed ideas require a pretrained model before pruning, which is costly to secure. In this paper, we propose a novel structural pruning approach to jointly learn the weights and structurally prune architectures of CNN models. The core element of our method is a Reinforcement Learning (RL) agent whose actions determine the pruning ratios of the CNN model's layers, and the resulting model's accuracy serves as its reward. We conduct the joint training and pruning by iteratively training the model's weights and the agent's policy, and we regularize the model's weights to align with the selected structure by the agent. The evolving model's weights result in a dynamic reward function for the agent, which prevents using prominent episodic RL methods with stationary environment assumption for our purpose. We address this challenge by designing a mechanism to model the complex changing dynamics of the reward function and provide a representation of it to the RL agent. To do so, we take a learnable embedding for each training epoch and employ a recurrent model to calculate a representation of the changing environment. We train the recurrent model and embeddings using a decoder model to reconstruct observed rewards. Such a design empowers our agent to effectively leverage episodic observations along with the environment representations to learn a proper policy to determine performant sub-networks of the CNN model. Our extensive experiments on CIFAR-10 and ImageNet using ResNets and MobileNets demonstrate the effectiveness of our method.