arXiv AI
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 3
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
arXiv:2607. 01444v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network must remain loaded.
arXiv Machine Learning
Aug 11
Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking
arXiv:2608. 08624v1 Announce Type: new Abstract: Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness and model efficiency, respectively.
arXiv Machine Learning
Jun 16
When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations
arXiv:2606. 16196v1 Announce Type: new Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment.
arXiv Machine Learning
Jun 25
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
arXiv:2606. 24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy.
arXiv AI
Jul 1
One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
arXiv:2508. 13836v2 Announce Type: replace-cross Abstract: Pruning is a core technique for compressing neural networks to improve computational efficiency.
arXiv AI
3d ago
GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical Data
GRIN+ is a new machine unlearning framework that targets fast and precise data erasure in imbalanced medical datasets. It separates unlearning‑specific knowledge from general representations by analyzing gradient contributions of forget and retain sets, introduces a class‑adaptive influence scoring to counter gradient dominance, and uses a direction‑constrained update to protect essential clinical knowledge. Benchmarks on skin cancer, brain tumor, and breast ultrasound data show that GRIN+ balances privacy, efficiency, and utility, achieving high diagnostic accuracy and faster runtime than existing methods.