mlsanityData to 14 Oct 2026

FedASAP: Activation Statistics-driven Structured Adaptive Pruning for Efficient Personalized Federated Learning for Lesion Segmentation on brain MRI

arXiv 2609.19042 ↗First posted 20 Jul 2026eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In medical imaging, developing robust deep learning models requires data from various domains. However, regulatory policies protecting patient privacy restrict data sharing. Federated learning (FL) addresses this by enabling collaborative model training without centralizing data. Yet, data heterogeneity across client centers requires personalized models to enhance performance. Clients with limited resources may struggle to efficiently train or deploy large deep neural networks. Adaptive model pruning tackles both challenges by reducing model size while enabling personalized FL adaptation. Although research has investigated adaptive pruning methods in FL, their effectiveness on dense prediction tasks like segmentation remains unexplored. To address this gap, we propose Activation Statistics-driven structured Adaptive Pruning (FedASAP), which uses activation-based features to guide filter removal for each client. By learning a lightweight classifier on per-filter activation statistics, FedASAP refines importance-score rankings and produces compact, personalized segmentation models in heterogeneous federated settings. Our results show the approach's effectiveness by achieving better Dice scores of 0.796 and 0.743, than state-of-the-art, while reducing parameter count by 45% and 73% on two multi-centric brain pathology segmentation datasets: Federated Tumour Segmentation (FeTS) and White Matter Hyperintensities (WMH), respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 20 Jul 2026.

Builds on

34 of 52 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  5. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  6. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  10. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  11. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 479
  12. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
22 more
  1. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
  2. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
  3. 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 55
  4. 2021The Federated Tumor Segmentation (FeTS) Challengecited by 50
  5. 2016Compression of Neural Machine Translation Models via Pruningcited by 44
  6. 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
  7. 2017An Entropy-based Pruning Method for CNN Compressioncited by 37
  8. 2022FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Servercited by 29
  9. 2022Personalizing Federated Medical Image Segmentation via Local Calibrationcited by 29
  10. 2021Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneitycited by 27
  11. 2022Federated Learning with GAN-based Data Synthesis for Non-IID Clientscited by 25
  12. 2022IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentationcited by 22
  13. 2022Mitigating Data Heterogeneity in Federated Learning with Data Augmentationcited by 21
  14. 2020Single Shot Structured Pruning Before Trainingcited by 19
  15. 2020FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learningcited by 14
  16. 2024FedMef: Towards Memory-efficient Federated Dynamic Pruningcited by 14
  17. 2021Blending Pruning Criteria for Convolutional Neural Networkscited by 13
  18. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Datacited by 11
  19. 2021An Experimental Study of Data Heterogeneity in Federated Learning Methods for Medical Imagingcited by 10
  20. 2022Iterative Activation-based Structured Pruningcited by 2
  21. 2023Filter Pruning based on Information Capacity and Independencecited by 2
  22. 2023Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networkscited by 2

Built on by

Not cited yet.