Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

• URL: http://arxiv.org/abs/2609.07803v1
• Date: Mon, 07 Sep 2026 17:44:19 GMT
• Title: Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
• Abstract summary: We study the effect of model pruning on forgetting and explanation reliability in deep neural networks.<n>Our results suggest that model compression should be evaluated beyond aggregate performance.
• Score: 6.220296131270666
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model pruning. Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity levels up to 95\%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability.

Related papers

• A Multi-Dimensional Evaluation of Explainability in Media Bias Detection [10.798797986346914]
  We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias s By Experts dataset.<n>We study BERT and RoBERTa as classifiers along three complementary axes: predictive performance, explanation plausibility, and mechanistic faithfulness.<n>Our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior.
  arXiv  Detail & Related papers  (2026-07-22T09:29:49Z)
• Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging [0.0]
  Post-hoc explanation methods are widely used to visualize model decisions in the form of saliency maps.<n>This paper analyzes how different explanation loss designs and supervision strengths influence both predictive performance and spatial faithfulness of explanations.
  arXiv  Detail & Related papers  (2026-05-11T06:27:55Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Investigating the Impact of Model Instability on Explanations and Uncertainty [43.254616360807496]
  We simulate uncertainty in text input by introducing noise at inference time. We find that high uncertainty doesn't necessarily imply low explanation plausibility. This suggests that noise-augmented models may be better at identifying salient tokens when uncertain.
  arXiv  Detail & Related papers  (2024-02-20T13:41:21Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Understanding Robust Overfitting from the Feature Generalization Perspective [61.770805867606796]
  Adversarial training (AT) constructs robust neural networks by incorporating adversarial perturbations into natural data. It is plagued by the issue of robust overfitting (RO), which severely damages the model's robustness. In this paper, we investigate RO from a novel feature generalization perspective.
  arXiv  Detail & Related papers  (2023-10-01T07:57:03Z)
• Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures [93.17009514112702]
  Pruning, setting a significant subset of the parameters of a neural network to zero, is one of the most popular methods of model compression. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood.
  arXiv  Detail & Related papers  (2023-04-25T07:42:06Z)
• Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images [12.844658658362325]
  Key concern in integrating machine learning models in medicine is the ability to interpret their reasoning. We propose a multi-layer attention mechanism that enforces consistent interpretations between attended convolutional layers. Our proposed method leverages weakly annotated medical imaging data and provides complete and faithful explanations to the model's prediction.
  arXiv  Detail & Related papers  (2022-06-06T17:38:00Z)
• SurvCaus : Representation Balancing for Survival Causal Inference [3.4161707164978137]
  In many pathologies, the outcome of interest is a (possibly censored) survival time. Our paper proposes theoretical guarantees for a representation balancing framework applied to counterfactual inference in a survival setting.
  arXiv  Detail & Related papers  (2022-03-29T15:33:55Z)
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy [70.71457102672545]
  We compare the impact of different training procedures for diabetic retinopathy grading. We investigate different aspects such as quantitative performance, statistics of the learned feature representations, interpretability and robustness to image distortions. Our results indicate that models from ImageNet pretraining report a significant increase in performance, generalization and robustness to image distortions.
  arXiv  Detail & Related papers  (2021-06-25T08:32:45Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.