用概率方法解决标签模糊问题，让模型自动判断哪个标签才是对的。
Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
- 用神经网络直接预测标签后验分布，实现高效推断。
- 在真实和合成数据集上准确率与效率均达当前最佳水平。
- 适合处理标注混乱的现实数据，如众包任务中的矛盾标签。
真实世界数据常存在噪声和模糊性。例如，在众包标注中，不同人工标注者可能为同一实例分配冲突的类别标签。部分标签学习（Partial-label learning, PLL）通过允许每个实例关联一组候选标签（其中仅一个正确）来应对这一挑战。早期的PLL方法虽近似真实标签后验分布，但计算成本高；近期深度学习方法提升了可扩展性，却依赖代理损失和启发式标签优化。本文提出一种新型概率框架，采用摊销变分推断（amortized variational inference）直接逼近真实标签的后验分布。该方法利用神经网络从输入数据中预测变分参数，实现高效推理。该方案融合深度学习的表达能力与概率建模的严谨性，且不依赖特定网络结构。理论分析与大量实验表明，该方法在准确率和效率方面均达到当前最优水平。
原文摘要 · Abstract (English)
Real-world data is frequently noisy and ambiguous. In crowdsourcing, for example, human annotators may assign conflicting class labels to the same instances. Partial-label learning (PLL) addresses this challenge by training classifiers when each instance is associated with a set of candidate labels, only one of which is correct. While early PLL methods approximate the true label posterior, they are often computationally intensive. Recent deep learning approaches improve scalability but rely on surrogate losses and heuristic label refinement. We introduce a novel probabilistic framework that directly approximates the posterior distribution over true labels using amortized variational inference. Our method employs neural networks to predict variational parameters from input data, enabling efficient inference. This approach combines the expressiveness of deep learning with the rigor of probabilistic modeling, while remaining architecture-agnostic. Theoretical analysis and extensive experiments on synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in both accuracy and efficiency.
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。