揭示模型预测不确定性中捷径学习的关键作用
Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
- 从认知不确定性和意见分歧双视角解析不确定性
- 发现捷径学习会引发模型间的分歧式不确定性
- 适用于关注模型可信度与决策可靠性的研究者
神经网络中预测不确定性的量化方法仍是活跃讨论话题。特别是，当前最先进的熵分解方法是否能真实反映模型（即认知）不确定性（EU），在‘无知’与‘意见分歧’两种观点间存在争议。本文旨在调和这一矛盾，认为两种视角均有其合理性，但源于不同的学习情境。关键发现是：捷径学习的存在决定了认知不确定性是否表现为模型间的分歧。
原文摘要 · Abstract (English)
The correct way to quantify predictive uncertainty in neural networks remains a topic of active discussion. In particular, it is unclear whether the state-of-the art entropy decomposition leads to a meaningful representation of model, or epistemic, uncertainty (EU) in the light of a debate that pits ignorance against disagreement perspectives. We aim to reconcile the conflicting viewpoints by arguing that both are valid but arise from different learning situations. Notably, we show that the presence of shortcuts is decisive for EU manifesting as disagreement.
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。