# Effective Fine-Tuning with Eigenvector Centrality Based Pruning

arXiv: https://arxiv.org/abs/2512.12543 · HTML: https://mlsanity.com/paper/2512.12543/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [Predicting Parameters in Deep Learning](https://mlsanity.com/paper/1306.0543/) (2013)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [Graph Structure of Neural Networks](https://mlsanity.com/paper/2007.06559/) (2020)
- [Methods for Pruning Deep Neural Networks](https://mlsanity.com/paper/2011.00241/) (2020)
- [Eigenvector centrality of nodes in multiplex networks](https://mlsanity.com/paper/1305.7445/) (2013)
- [A Deeper Look into Convolutions via Eigenvalue-based Pruning](https://mlsanity.com/paper/2102.02804/) (2021)
- [LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models](https://mlsanity.com/paper/2410.13299/) (2024)

## Built on by (most cited first, 1 of 1)

- [Centrality-Based Pruning for Efficient Echo State Networks](https://mlsanity.com/paper/2603.20684/) (2026)

## Abstract (arXiv)

In social media networks a small number of highly influential users can drive large scale changes in discourse across multiple communities. Small shifts in the behavior of these users are often sufficient to propagate widely throughout the network. A similar phenomenon occurs during neural network fine tuning. Conventional fine tuning of convolutional neural networks typically adds a new linear classification layer on top of a large pre trained model. Instead we argue that improved adaptation can be achieved by first pruning the network to retain only the most important neurons and then performing fine tuning. We propose a graph theory based method for pruning neural networks that is designed to improve fine tuning performance. In this method each neuron is represented as a node and edges encode similarity between neurons. Neurons are pruned based on importance scores computed using eigenvector centrality. The resulting pruned network is then fine tuned using only the most central neurons. We evaluate the proposed method on VGGNet EfficientNet and ResNet models using the TF Flowers Caltech one zero one and Oxford Flowers one zero two datasets. The proposed approach achieves higher classification accuracy while significantly reducing model complexity. On the Oxford Flowers one zero two dataset the method achieves forty eight percent classification accuracy compared to thirty percent accuracy obtained by the baseline VGGNet model.