提出新方法实现稳定且可识别的跨域翻译
Diversified Flow Matching with Translation Identifiability
- 基于微分方程构建统一映射函数，解决多源分布对齐问题
- 首次实现保证翻译可识别性的ODE框架，支持轨迹信息输出
- 适用于单细胞演化分析、机器人路径规划等需轨迹的应用
多样化分布匹配（DDM）旨在寻找一个统一的变换函数，将多样化的条件源分布映射到目标分布，以解决无配对域翻译中的内容错位问题，并实现翻译可识别性。然而，由于对变换函数的约束，现有方法仅能使用生成对抗网络（GANs），而GAN训练不稳定，且不提供传输轨迹信息——这对单细胞演化分析和机器人路径规划等应用至关重要。本文提出多样化流匹配（DFM），一种基于常微分方程（ODE）的DDM框架。针对流匹配（FM）学习的是变换函数的速度而非函数本身这一挑战，设计了定制的双层优化损失、非线性插值器和结构重构方案，成功实现了可实施的统一映射。据我们所知，DFM是首个保证翻译可识别性的基于ODE的方法。在合成数据与真实世界数据集上的实验验证了该方法的有效性。
原文摘要 · Abstract (English)
Diversified distribution matching (DDM) finds a unified translation function mapping a diverse collection of conditional source distributions to their target counterparts. DDM was proposed to resolve content misalignment issues in unpaired domain translation, achieving translation identifiability. However, DDM has only been implemented using GANs due to its constraints on the translation function. GANs are often unstable to train and do not provide the transport trajectory information -- yet such trajectories are useful in applications such as single-cell evolution analysis and robot route planning. This work introduces diversified flow matching (DFM), an ODE-based framework for DDM. Adapting flow matching (FM) to enforce a unified translation function as in DDM is challenging, as FM learns the translation function's velocity rather than the translation function itself. A custom bilevel optimization-based training loss, a nonlinear interpolant, and a structural reformulation are proposed to address these challenges, offering a tangible implementation. To our knowledge, DFM is the first ODE-based approach guaranteeing translation identifiability. Experiments on synthetic and real-world datasets validate the proposed method.
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。