在固定时间内提升深度学习模型性能，通过动态采样优化训练效率。
Accelerating Deep Learning with Fixed Time Budget
- 根据样本重要性动态排序，实现时间约束下的高效训练
- 在图像分类与回归任务中显著提升多种主流模型性能
- 适合边缘计算与联邦学习等对时间敏感的场景
现代深度学习的成功依赖于海量训练数据和大型模型结构，但二者均导致训练时间过长。在边缘学习和联邦学习等实际应用中，时间预算有限，亟需更高效的训练方法。本文提出一种通用技术，可在固定时间预算内对任意深度学习模型进行训练，利用样本重要性和动态排序机制。该方法在计算机视觉的分类与回归任务中进行了广泛评估，结果一致表明，所提方法显著提升了多种先进模型的学习性能。
原文摘要 · Abstract (English)
The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the learning capability of the model. However, both these factors result in prolonged training time. In some practical applications such as edge-based learning and federated learning, limited-time budgets necessitate more efficient training methods. This paper proposes an effective technique for training arbitrary deep learning models within fixed time constraints utilizing sample importance and dynamic ranking. The proposed method is extensively evaluated in both classification and regression tasks in computer vision. The results consistently show clear gains achieved by the proposed method in improving the learning performance of various state-of-the-art deep learning models in both regression and classification tasks.
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。