利用过拟合动态检测并修正极端噪声标签，无需提前停止
Selfish Evolution: Making Discoveries in Extreme Label Noise with the Help of Overfitting Dynamics
- 让模型在噪声数据上持续训练，通过过拟合过程捕捉标签异常模式
- 在超新星探测数据集上实现标签纠正，准确率提升显著
- 适用于弱监督场景，特别适合标签质量差的天文数据
针对天体物理应用中标签稀缺的问题，我们提出一种新方法——自我进化（Selfish Evolution），可在弱监督条件下检测并修正错误标签。不同于依赖早停的方法，该方法允许模型在噪声数据上持续训练，随后引入过拟合机制，使模型对单个样本过度拟合。在此过程中，模型的“演化”轨迹（时序空间立方体）蕴含了标签噪声程度及其正确版本的关键信息。我们训练一个辅助网络，基于这些演化特征来修正潜在错误标签。该方法以闭环方式集成，能自动收敛至高清洁度数据集，且不依赖干预时模型的状态。我们在超新星搜寻数据集上进行评估，并在标准的MNIST数据集上验证其效率。
原文摘要 · Abstract (English)
Motivated by the scarcity of proper labels in an astrophysical application, we have developed a novel technique, called Selfish Evolution, which allows for the detection and correction of corrupted labels in a weakly supervised fashion. Unlike methods based on early stopping, we let the model train on the noisy dataset. Only then do we intervene and allow the model to overfit to individual samples. The ``evolution'' of the model during this process reveals patterns with enough information about the noisiness of the label, as well as its correct version. We train a secondary network on these spatiotemporal ``evolution cubes'' to correct potentially corrupted labels. We incorporate the technique in a closed-loop fashion, allowing for automatic convergence towards a mostly clean dataset, without presumptions about the state of the network in which we intervene. We evaluate on the main task of the Supernova-hunting dataset but also demonstrate efficiency on the more standard MNIST dataset.
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。