无需插值的双流匹配方法，提升连续归一化流训练效率与性能。
DFM: Interpolant-free Dual Flow Matching
- 提出无插值的双向流匹配框架，同时优化正向与反向向量场。
- 在SMAP数据集上优于最大似然与传统流匹配方法，异常检测准确率领先。
- 适用于需要高精度建模的无监督异常检测任务。
连续归一化流（CNF）能以表达能力强的无限长度架构建模数据分布，但最大似然训练需求解常微分方程（ODE），计算成本高。近期提出的流匹配（FM）框架通过回归目标简化训练过程，使用插值前向向量场。本文提出一种无需显式假设向量场的插值自由双流匹配（DFM）方法，通过新目标函数同时优化前向与反向向量场模型，促进正向与反向变换的双射性。在SMAP无监督异常检测任务中，DFM表现优于基于最大似然或传统流匹配训练的CNF，在先进指标上达到最优性能。
原文摘要 · Abstract (English)
Continuous normalizing flows (CNFs) can model data distributions with expressive infinite-length architectures. But this modeling involves computationally expensive process of solving an ordinary differential equation (ODE) during maximum likelihood training. Recently proposed flow matching (FM) framework allows to substantially simplify the training phase using a regression objective with the interpolated forward vector field. In this paper, we propose an interpolant-free dual flow matching (DFM) approach without explicit assumptions about the modeled vector field. DFM optimizes the forward and, additionally, a reverse vector field model using a novel objective that facilitates bijectivity of the forward and reverse transformations. Our experiments with the SMAP unsupervised anomaly detection show advantages of DFM when compared to the CNF trained with either maximum likelihood or FM objectives with the state-of-the-art performance metrics.
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。