# Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.10526 · HTML: https://mlsanity.com/paper/2509.10526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [Graph Matching Networks for Learning the Similarity of Graph Structured Objects](https://mlsanity.com/paper/1904.12787/) (2019)
- [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://mlsanity.com/paper/1804.03230/) (2018)
- [Provable Filter Pruning for Efficient Neural Networks](https://mlsanity.com/paper/1911.07412/) (2019)
- [EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning](https://mlsanity.com/paper/2007.02491/) (2020)
- [AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference](https://mlsanity.com/paper/1805.08941/) (2018)
- [AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates](https://mlsanity.com/paper/1907.03141/) (2019)
- [DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation](https://mlsanity.com/paper/2004.02164/) (2020)
- [Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning](https://mlsanity.com/paper/2102.03214/) (2021)
- [MuZero with Self-competition for Rate Control in VP9 Video Compression](https://mlsanity.com/paper/2202.06626/) (2022)
- [Learning to Prune Filters in Convolutional Neural Networks](https://mlsanity.com/paper/1801.07365/) (2018)
- [Neural Network Pruning Through Constrained Reinforcement Learning](https://mlsanity.com/paper/2110.08558/) (2021)

## Abstract (arXiv)

This paper presents a novel approach to neural network pruning by integrating a graph-based observation space into an AutoML framework to address the limitations of existing methods. Traditional pruning approaches often depend on hand-crafted heuristics and local optimization perspectives, which can lead to suboptimal performance and inefficient pruning strategies. Our framework transforms the pruning process by introducing a graph representation of the target neural network that captures complete topological relationships between layers and channels, replacing the limited layer-wise observation space with a global view of network structure. The core innovations include a Graph Attention Network (GAT) encoder that processes the network's graph representation and generates a rich embedding. Additionally, for the action space we transition from continuous pruning ratios to fine-grained binary action spaces which enables the agent to learn optimal channel importance criteria directly from data, moving away from predefined scoring functions. These contributions are modelled within a Constrained Markov Decision Process (CMDP) framework, allowing the agent to make informed pruning decisions while adhering to resource constraints such as target compression rates. For this, we design a self-competition reward system that encourages the agent to outperform its previous best performance while satisfying the defined constraints. We demonstrate the effectiveness of our approach through extensive experiments on benchmark datasets including CIFAR-10, CIFAR-100, and ImageNet. The experiments show that our method consistently outperforms traditional pruning techniques, showing state-of-the-art results while learning task-specific pruning strategies that identify functionally redundant connections beyond simple weight magnitude considerations.