动态调整样本权重，让模型先学简单样本再攻难点。
Adaptively Point-weighting Curriculum Learning
- 根据训练损失自动分配样本权重，随训练状态变化调节难易度。
- 理论证明方法有效提升训练效果、稳定性和泛化能力。
- 适合需要高效训练深度网络的场景，尤其在数据分布不均时。
课程学习（CL）模拟人类学习过程，先学简单样本再学难样本，已成为训练深度网络的有效方法。然而，现有自动课程学习方法在整个训练过程中始终偏好简单样本，未能随网络训练状态动态调整，如同缺乏个性化教学，可能延缓学习进度。为此，本文提出自适应点权重课程学习（APW）方法，基于每个样本的训练损失为其分配权重，其权重策略遵循由易到难的训练范式，并依据当前网络训练状态进行动态调整。我们对APW进行了理论分析，涵盖训练有效性、训练稳定性及泛化性能。实验结果验证了理论发现，并展示了所提APW方法的优越性。
原文摘要 · Abstract (English)
Curriculum learning (CL) mimics human learning, in which easy samples are learned first, followed by harder samples, and has become an effective method for training deep networks. However, many existing automatic CL methods maintain a preference for easy samples during the entire training process regardless of the constantly evolving training state. This is just like a human curriculum that fails to provide individualized instruction, which can delay learning progress. To address this issue, we propose an adaptively point-weighting (APW) curriculum learning method that assigns a weight to each training sample based on its training loss. The weighting strategy of APW follows the easy-to-hard training paradigm, guided by the current training state of the network. We present a theoretical analysis of APW, including training effectiveness, training stability, and generalization performance. Experimental results validate these theoretical findings and demonstrate the superiority of the proposed APW method.
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。