基于部分最优传输理论，为部分域适应提供可解释的权重设计与性能保证。
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
- 利用部分最优传输构建理论框架，给出泛化误差上界。
- 推导出源数据加权损失的显式最优权重表达式。
- 提出WARMPOT算法，实验显示优于现有方法。
在实际应用中，目标域标注数据稀少而相关源域数据丰富。当目标标签空间是源标签空间的子集时，进入部分域适应（PDA）场景。传统PDA方法通常最小化域对齐项和加权源域经验损失，但缺乏理论支撑，多数加权策略为启发式。本文基于部分最优传输推导出PDA问题的泛化边界，验证了使用部分Wasserstein距离作为域对齐项的合理性，并导出经验源损失权重的理论表达式。受此启发，提出实用算法WARMPOT。大量数值实验表明，该方法性能优于近期主流方案，且所提权重显著提升效果。
原文摘要 · Abstract (English)
In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setting of interest arises when the target label space is a subset of the source label space, leading to the framework of partial domain adaptation (PDA). Typical approaches to PDA involve minimizing a domain alignment term and a weighted empirical loss on the source data, with the aim of transferring knowledge between domains. However, a theoretical basis for this procedure is lacking, and in particular, most existing weighting schemes are heuristic. In this work, we derive generalization bounds for the PDA problem based on partial optimal transport. These bounds corroborate the use of the partial Wasserstein distance as a domain alignment term, and lead to theoretically motivated explicit expressions for the empirical source loss weights. Inspired by these bounds, we devise a practical algorithm for PDA, termed WARMPOT. Through extensive numerical experiments, we show that WARMPOT is competitive with recent approaches, and that our proposed weights improve on existing schemes.
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。