动态调整数据批次中类别比例，加速模型收敛。
Learn2Mix: Training Neural Networks Using Adaptive Data Integration
- 根据错误率动态调整每批数据的类别比例
- 在资源受限和类别不平衡下收敛更快
- 适合数据不均衡场景下的高效训练
在资源受限环境下加速模型收敛对高效神经网络训练至关重要。本文提出 learn2mix，一种自适应调整批次内类别比例的新训练策略，聚焦于错误率较高的类别。与传统使用静态类别比例的方法不同，learn2mix 在训练过程中持续调整类别比例，从而实现更快收敛。在基准数据集上的实证评估表明，使用 learn2mix 训练的神经网络在分类、回归和重建任务中均比现有方法收敛更快，且在有限训练资源和类别不平衡条件下表现更优。实验结果得到理论分析的支持。
原文摘要 · Abstract (English)
Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proportions within batches, focusing on classes with higher error rates. Unlike classical training methods that use static class proportions, learn2mix continually adapts class proportions during training, leading to faster convergence. Empirical evaluations on benchmark datasets show that neural networks trained with learn2mix converge faster than those trained with existing approaches, achieving improved results for classification, regression, and reconstruction tasks under limited training resources and with imbalanced classes. Our empirical findings are supported by theoretical analysis.
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。