arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.01795cs.LGcs.AIcs.CVcs.ROstat.ML
收藏

分数阶扩散桥模型

Fractional Diffusion Bridge Models

Fraunhofer HHI(弗劳恩霍夫研究所);Ghent University–imec FlandersMake–MIRO(根特大学–imec 荷兰弗拉芒Make–MIRO);Technical University of Munich(慕尼黑技术大学);Technical University of Berlin(柏林技术大学);University of Potsdam(波茨坦大学);University of Birmingham(伯明翰大学);Imperial College London(伦敦帝国理工学院)

Gabriel Nobis, Maximilian Springenberg, Arina Belova, Rembert Daems, Christoph Knochenhauer, Manfred Opper, Tolga Birdal, Wojciech Samek

AI总结:

针对标准扩散桥无法捕捉真实过程非马尔可夫特性的问题,提出分数阶扩散桥模型(FDBM),利用fBM的马尔可夫近似实现可处理推断,并应用于蛋白质构象预测与未配对图像转换,性能优于布朗基线。

摘要:

我们提出了分数阶扩散桥模型(FDBM),这是一种由丰富且非马尔可夫的分数阶布朗运动(fBM)近似所驱动的新型生成式扩散桥框架。真实的随机过程表现出一定程度的记忆效应(时间上的相关性)、长程依赖性、粗糙性和反常扩散现象,由于使用布朗运动(BM),这些现象在标准扩散或桥建模中未被捕捉到。作为补救,利用最近提出的fBM马尔可夫近似(MA-fBM),我们构建了FDBM,在保留fBM非马尔可夫性质的同时实现了可处理的推断。我们证明了保耦合生成式扩散桥的存在性,并利用它从成对训练数据中进行未来状态预测。然后,我们将公式扩展到薛定谔桥问题,并推导出一种有原则的损失函数来学习未配对数据转换。我们在两项任务上评估了FDBM:从对齐数据预测未来蛋白质构象,以及未配对图像转换。在这两种设置中,与布朗基线相比,FDBM均取得了更优的性能,在蛋白质结构预测中产生了更低的C$_α$原子位置均方根偏差(RMSD),在未配对图像转换中产生了更低的Fréchet Inception Distance(FID)。

英文摘要:

We present Fractional Diffusion Bridge Models (FDBM), a novel generative diffusion bridge framework driven by an approximation of the rich and non-Markovian fractional Brownian motion (fBM). Real stochastic processes exhibit a degree of memory effects (correlations in time), long-range dependencies, roughness and anomalous diffusion phenomena that are not captured in standard diffusion or bridge modeling due to the use of Brownian motion (BM). As a remedy, leveraging a recent Markovian approximation of fBM (MA-fBM), we construct FDBM that enable tractable inference while preserving the non-Markovian nature of fBM. We prove the existence of a coupling-preserving generative diffusion bridge and leverage it for future state prediction from paired training data. We then extend our formulation to the Schrödinger bridge problem and derive a principled loss function to learn the unpaired data translation. We evaluate FDBM on both tasks: predicting future protein conformations from aligned data, and unpaired image translation. In both settings, FDBM achieves superior performance compared to the Brownian baselines, yielding lower root mean squared deviation (RMSD) of C$_α$ atomic positions in protein structure prediction and lower Fréchet Inception Distance (FID) in unpaired image translation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑