设计自定义损失函数，让模型训练结果更稳定可靠。
Learning to be Reproducible: Custom Loss Design for Robust Neural Networks
- 提出自定义损失函数，降低初始化和数据打乱带来的随机波动
- 在图像分类与时间序列任务中显著提升训练稳定性，精度不下降
- 适合追求可复现性与鲁棒性的模型研发人员使用
为提升深度学习模型的可复现性与可靠性，本文针对当前训练方法缺乏保证跨运行一致性与鲁棒性的机制这一关键问题展开研究。实证分析表明，即使在固定初始化与训练条件下，模型准确率仍存在显著波动。为此，我们提出一种自定义损失函数（CLF），通过调节参数显式平衡预测精度与训练稳定性，有效降低权重初始化与数据打乱等随机因素对训练结果的影响。在多种架构的图像分类与时间序列预测任务上的大量实验验证了该方法的有效性：在不牺牲预测性能的前提下，显著提升训练鲁棒性。结果表明，CLF是一种高效且可靠的神经网络稳定性增强策略。
原文摘要 · Abstract (English)
To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis reveals that even under controlled initialization and training conditions, the accuracy of the model can exhibit significant variability. To address this issue, we propose a Custom Loss Function (CLF) that reduces the sensitivity of training outcomes to stochastic factors such as weight initialization and data shuffling. By fine-tuning its parameters, CLF explicitly balances predictive accuracy with training stability, leading to more consistent and reliable model performance. Extensive experiments across diverse architectures for both image classification and time series forecasting demonstrate that our approach significantly improves training robustness without sacrificing predictive performance. These results establish CLF as an effective and efficient strategy for developing more stable, reliable and trustworthy neural networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。