提出新弱监督学习方法，放宽假设并改进评估体系。
Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions
- 引入置信度差分类新范式，解决标注不完整问题。
- 在互补标签学习中放松数据生成假设，提升模型鲁棒性。
- 构建部分标签学习评估框架，推动公平实验对比。
深度学习近年取得巨大成功，得益于高质量标注数据的可用性。然而，现实应用中这一条件常难以满足。弱监督学习旨在利用不完整、不精确或错误的监督信息训练准确模型。本文综述该领域最新进展，涵盖新监督范式、假设松弛及实用解决方案。首先，提出一种新型弱监督二分类任务——置信度差分类，并给出一致的求解方法。其次，研究互补标签学习这一多类弱监督分类问题，所提方法对数据生成过程的假设比现有方法更宽松。最后，为部分标签学习这一流行多类弱监督学习问题，构建评估框架，以促进该领域算法的公平与真实评估。
原文摘要 · Abstract (English)
Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often not met in real-world applications. Weakly supervised learning aims to train an accurate model with incomplete, inexact, or inaccurate supervision. In this chapter, we will discuss recent advances in this field, including new supervision paradigms, relaxed assumptions, and practical solutions. First, we introduce a new weakly supervised binary classification problem called confidence-difference classification and propose consistent approaches to solve it. Next, we investigate complementary-label learning, a weakly supervised multi-class classification problem. Our proposed approaches are based on more relaxed assumptions about the data generation process than existing consistent approaches. Lastly, we present an evaluation framework for partial-label learning, another popular multi-class weakly supervised learning problem, in order to promote fair and realistic evaluation of algorithms in this field.
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。