一句话：对16种深度学习模型修复方法进行大规模实证评估，覆盖修复效果及鲁棒性、公平性与向后兼容性等影响。
深度学习系统在自动驾驶、智能医疗等场景中广泛部署，但模型故障会带来风险，已有大量修复方法却缺乏统一评估。本文对16种先进深度学习模型修复方法开展大规模实证研究，涵盖模型级、层级和神经元级三类，在统一实验设置下使用多种数据集、模型架构和应用领域，不仅评估其主要修复效果，还考察对鲁棒性、公平性和向后兼容性等关键属性的影响。研究发现，模型级方法通常修复效果更优；但没有任何单一方法能在提升修复性能的同时改善准确率并保持所有其他属性，提示学术界需关注并缓解这些副作用。该工作为工业界和学术界总结了关键发现，并指出未来研究方向。
Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empirical study on 16 state-of-the-art DL model fixing approaches, spanning model-level, layer-level, and neuron-level categories, to comprehensively evaluate their performance. We assess not only their fixing effectiveness (their primary purpose) but also their impact on other critical properties, such as robustness, fairness, and backward compatibility. To ensure comprehensive and fair evaluation, we employ a diverse set of datasets, model architectures, and application domains within a uniform experimental setup for experimentation. We summarize several key findings with implications for both industry and academia. For example, model-level approaches demonstrate superior fixing effectiveness compared to others. No single approach can achieve the best fixing performance while improving accuracy and maintaining all other properties. Thus, academia should prioritize research on mitigating these side effects. These insights highlight promising directions for future exploration in this field.
@inproceedings{abs-2512-23745,
title = {A Comprehensive Study of Deep Learning Model Fixing Approaches},
author = {Hanmo You and Zan Wang and Zishuo Dong and Luanqi Mo and Jianjun Zhao and Junjie Chen},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3764528}
}