mlsanityData to 14 Oct 2026

Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19

arXiv 2509.05322 ↗First posted 30 Aug 2025cs.CV cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Randomly Wired Neural Networks (RWNNs) serve as a valuable testbed for investigating the impact of network topology in deep learning by capturing how different connectivity patterns impact both learning efficiency and model performance. At the same time, they provide a natural framework for exploring edge-centric network measures as tools for pruning and optimization. In this study, we investigate three edge-centric network measures: Forman-Ricci curvature (FRC), Ollivier-Ricci curvature (ORC), and edge betweenness centrality (EBC), to compress RWNNs by selectively retaining important synapses (or edges) while pruning the rest. As a baseline, RWNNs are trained for COVID-19 chest x-ray image classification, aiming to reduce network complexity while preserving performance in terms of accuracy, specificity, and sensitivity. We extend prior work on pruning RWNN using ORC by incorporating two additional edge-centric measures, FRC and EBC, across three network generators: Erd"os-R'enyi (ER) model, Watts-Strogatz (WS) model, and Barab'asi-Albert (BA) model. We provide a comparative analysis of the pruning performance of the three measures in terms of compression ratio and theoretical speedup. A central focus of our study is to evaluate whether FRC, which is computationally more efficient than ORC, can achieve comparable pruning effectiveness. Along with performance evaluation, we further investigate the structural properties of the pruned networks through modularity and global efficiency, offering insights into the trade-off between modular segregation and network efficiency in compressed RWNNs. Our results provide initial evidence that FRC-based pruning can effectively simplify RWNNs, offering significant computational advantages while maintaining performance comparable to ORC.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 97 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

38 of 97 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2014Going Deeper with Convolutionscited by 4,241
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  8. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  9. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  11. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  12. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
26 more
  1. 2018Rethinking the Value of Network Pruningcited by 599
  2. 2020What is the State of Neural Network Pruning?cited by 583
  3. 2019Importance Estimation for Neural Network Pruningcited by 541
  4. 2019The State of Sparsity in Deep Neural Networkscited by 476
  5. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
  6. 2020COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Imagescited by 264
  7. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 254
  8. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  9. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 134
  10. 2019Exploring Randomly Wired Neural Networks for Image Recognitioncited by 103
  11. 2020COVID-19 Image Data Collectioncited by 101
  12. 2020CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray imagescited by 68
  13. 2020Graph Structure of Neural Networkscited by 68
  14. 2020Deep-COVID: Predicting COVID-19 From Chest X-Ray Images Using Deep Transfer Learningcited by 67
  15. 2020COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Imagescited by 60
  16. 2020Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural networkcited by 43
  17. 2021Recent Advances on Neural Network Pruning at Initializationcited by 41
  18. 2020COVID-CAPS: A Capsule Network-based Framework for Identification of COVID-19 cases from X-ray Imagescited by 34
  19. 2020Diagnosing COVID-19 Pneumonia from X-Ray and CT Images using Deep Learning and Transfer Learning Algorithmscited by 24
  20. 2017Augmentor: An Image Augmentation Library for Machine Learningcited by 14
  21. 2020Extracting possibly representative COVID-19 Biomarkers from X-Ray images with Deep Learning approach and image data related to Pulmonary Diseasescited by 13
  22. 2021Exploring Robust Architectures for Deep Artificial Neural Networkscited by 11
  23. 2020RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flowcited by 4
  24. 2020COVIDLite: A depth-wise separable deep neural network with white balance and CLAHE for detection of COVID-19cited by 2
  25. 2014From Caenorhabditis elegans to the Human Connectome: A Specific Modular Organisation Increases Metabolic, Functional, and Developmental Efficiencycited by 1
  26. 2016Modular Segregation of Structural Brain Networks Supports the Development of Executive Function in Youthcited by 1

Built on by

Not cited yet.