# Learning to Prune Filters in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1801.07365 · HTML: https://mlsanity.com/paper/1801.07365/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2018.

## Built on by (most cited first, 25 of 25)

- [Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN](https://mlsanity.com/paper/2107.14444/) (2021)
- [Equal Bits: Enforcing Equally Distributed Binary Network Weights](https://mlsanity.com/paper/2112.03406/) (2021)
- [Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment](https://mlsanity.com/paper/2403.19490/) (2024)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges](https://mlsanity.com/paper/2205.03824/) (2022)
- [Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training](https://mlsanity.com/paper/2303.13635/) (2023)
- [Holistic Adversarially Robust Pruning](https://mlsanity.com/paper/2412.14714/) (2024)
- [Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation](https://mlsanity.com/paper/2110.09674/) (2021)
- [Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer](https://mlsanity.com/paper/2306.17504/) (2023)
- [UPSCALE: Unconstrained Channel Pruning](https://mlsanity.com/paper/2307.08771/) (2023)
- [Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction](https://mlsanity.com/paper/2112.15445/) (2021)
- [L2PF -- Learning to Prune Faster](https://mlsanity.com/paper/2101.02663/) (2021)
- [Evolving Transferable Neural Pruning Functions](https://mlsanity.com/paper/2110.10876/) (2021)
- [Exploring Gradient Flow Based Saliency for DNN Model Compression](https://mlsanity.com/paper/2110.12477/) (2021)
- [Learning Activation Functions for Sparse Neural Networks](https://mlsanity.com/paper/2305.10964/) (2023)
- [Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting](https://mlsanity.com/paper/2308.07939/) (2023)
- [Convolutional Neural Network Simplification with Progressive Retraining](https://mlsanity.com/paper/2101.04699/) (2021)
- [Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation](https://mlsanity.com/paper/2104.01303/) (2021)
- [Real-Time Online Skeleton Extraction and Gesture Recognition on Pepper](https://mlsanity.com/paper/2206.11376/) (2022)
- [Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning](https://mlsanity.com/paper/2301.11063/) (2023)
- [CP-CNN: Core-Periphery Principle Guided Convolutional Neural Network](https://mlsanity.com/paper/2304.10515/) (2023)
- [A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems](https://mlsanity.com/paper/2312.03889/) (2023)
- [Pruning Convolutional Filters via Reinforcement Learning with Entropy Minimization](https://mlsanity.com/paper/2312.04918/) (2023)
- [Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning](https://mlsanity.com/paper/2509.10526/) (2025)
- [Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation](https://mlsanity.com/paper/2601.19794/) (2026)

## Abstract (arXiv)

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing resource consumptions. This paper presents a learning algorithm to simplify and speed up these CNNs. Specifically, we introduce a "try-and-learn" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way. With the help of a novel reward function, our agents removes a significant number of filters in CNNs while maintaining performance at a desired level. Moreover, this method provides an easy control of the tradeoff between network performance and its scale. Per- formance of our algorithm is validated with comprehensive pruning experiments on several popular CNNs for visual recognition and semantic segmentation tasks.