用可信度感知机制改进自适应学习，让模型先学真正简单的样本。
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
- 基于证据神经网络，用不确定性估计判断样本难易程度
- 在多个数据集上分类准确率超越现有自适应学习方法
- 方法可解释性强，适合需要信任决策过程的场景
自适应学习（SPL）通过从低损失样本开始逐步学习，模拟人类由易到难的学习过程，有效提升模型性能与训练效率。然而，损失值小的样本未必可靠，可能并非对模型而言真正简单。为此，本文提出一种基于证据神经网络的不确定性感知自适应学习方法（UASPL），在主观逻辑框架下引入通用损失函数，同时融合预测可靠性与不确定性估计，实现更精准的样本选择。该损失函数可扩展至多种SPL变体，并通过耦合样本选择偏好保持过程可解释性。在多个数据集上的实验表明，UASPL在分类性能、可解释性与通用性方面均优于现有SPL方法。代码已开源：https://github.com/treelife979/UASPL。
原文摘要 · Abstract (English)
Self-paced learning (SPL) is an effective learning paradigm that simulates the human learning process by progressing from easy to difficult samples based on the value of the loss function during the learning process. It has shown great potential in improving model performance and training efficiency. However, the prediction results of samples with smaller loss values are not necessarily reliable, indicating that such samples are not always simple samples for the model. Hence, this article proposes an uncertainty-aware self-paced learning based on evidential neural networks, termed UASPL, which integrates predictive reliability into sample selection through a general loss function within the Subjective Logic framework. This loss function incorporates uncertainty estimation and can be extended to different variants of SPL. Moreover, this loss function couples a sample selection preference, thereby ensuring the interpretability of the sample selection process. Finally, the experimental results on multiple datasets show that UASPL outperforms other SPL methods in terms of classification performance, interpretability, and generality. The source code is available at: https://github.com/treelife979/UASPL.
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。