# Training-Free Restoration of Pruned Neural Networks

arXiv: https://arxiv.org/abs/2502.08474 · HTML: https://mlsanity.com/paper/2502.08474/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (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)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [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)
- [NISP: Pruning Networks using Neuron Importance Score Propagation](https://mlsanity.com/paper/1711.05908/) (2017)
- [Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon](https://mlsanity.com/paper/1705.07565/) (2017)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Zero-shot Knowledge Transfer via Adversarial Belief Matching](https://mlsanity.com/paper/1905.09768/) (2019)
- [Data-free parameter pruning for Deep Neural Networks](https://mlsanity.com/paper/1507.06149/) (2015)
- [Data-Free Adversarial Distillation](https://mlsanity.com/paper/1912.11006/) (2019)
- [EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning](https://mlsanity.com/paper/2007.02491/) (2020)
- [Towards Efficient Model Compression via Learned Global Ranking](https://mlsanity.com/paper/1904.12368/) (2019)
- [Neural Network Pruning with Residual-Connections and Limited-Data](https://mlsanity.com/paper/1911.08114/) (2019)
- [Data-Independent Neural Pruning via Coresets](https://mlsanity.com/paper/1907.04018/) (2019)

## Built on by (most cited first, 2 of 2)

- [BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression](https://mlsanity.com/paper/2509.25136/) (2025)
- [Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit](https://mlsanity.com/paper/2609.12337/) (2026)

## Abstract (arXiv)

Although network pruning has been highly popularized to compress deep neural networks, its resulting accuracy heavily depends on a fine-tuning process that is often computationally expensive and requires the original data. However, this may not be the case in real-world scenarios, and hence a few recent works attempt to restore pruned networks without any expensive retraining process. Their strong assumption is that every neuron being pruned can be replaced with another one quite similar to it, but unfortunately this does not hold in many neural networks, where the similarity between neurons is extremely low in some layers. In this article, we propose a more rigorous and robust method of restoring pruned networks in a fine-tuning free and data-free manner, called LBYL (Leave Before You Leave). LBYL significantly relaxes the aforementioned assumption in a way that each pruned neuron leaves its pieces of information to as many preserved neurons as possible and thereby multiple neurons together obtain a more robust approximation to the original output of the neuron who just left. Our method is based on a theoretical analysis on how to formulate the reconstruction error between the original network and its approximation, which nicely leads to a closed form solution for our derived loss function. Through the extensive experiments, LBYL is confirmed to be indeed more effective to approximate the original network and consequently able to achieve higher accuracy for restored networks, compared to the recent approaches exploiting the similarity between two neurons. The very first version of this work, which contains major technical and theoretical components, was submitted to NeurIPS 2021 and ICML 2022.