通过一致性预测实现可靠选择性分类，仅在所有模型一致时才预测。
Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach
- 基于嵌入空间的Lipschitz约束构建一致分类头版本空间。
- 为每个样本生成可验证的标签集合，仅当所有一致模型同意时才预测。
- 提出贪心查询策略，适用于预算有限的主动学习场景。
我们研究固定池（或归纳）设置下的选择性分类与拒答问题，其中未标记样本池预先给定，只能查询其中部分样本的标签。核心思想是通过一致性视角看待选择性预测：在嵌入空间中，结合已查询标签和Lipschitz边界约束，定义了满足一致性条件的分类头版本空间。我们推导出每个池内点的上下界Lipschitz边界，从而为每个点生成一个包含版本空间中所有分类头预测结果的认证有效标签集。模型仅在所有一致头输出相同标签时才进行预测，否则拒绝回答。此外，我们提出一种单调子模几何代理作为预算查询的近似目标，并证明贪心算法能保持标准近似因子。
原文摘要 · Abstract (English)
We consider selective classification with abstention in the fixed-pool (or transductive) setting, where the unlabeled pool is given beforehand and only a subset of points can be queried for labels. Our main insight is to view selective prediction through agreement: given queried labels and Lipschitz margin constraints in an embedding space, the version space of Lipschitz-consistent classification heads is well defined. We obtain upper and lower Lipschitz margin bounds that define, for each pool point, a set of certified valid labels containing the prediction of every head in the version space. The model therefore predicts only when the label is forced (i.e., all consistent heads agree), and abstains otherwise. We also propose a monotone submodular geometric proxy for budgeted querying, and show that a greedy algorithm retains the standard approximation factor.
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。