Effective Fine-Tuning with Eigenvector Centrality Based Pruning
This work addresses the challenge of efficient model adaptation for researchers and practitioners in deep learning, though it is incremental as it builds on existing pruning and fine-tuning techniques.
The paper tackles the problem of improving fine-tuning performance in convolutional neural networks by proposing a pruning method based on eigenvector centrality to retain only the most important neurons, resulting in higher classification accuracy and reduced model complexity, such as achieving 48% accuracy compared to 30% on the Oxford Flowers 102 dataset.
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.