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 2112.03379cs.LGcs.CV
收藏

面向时间序列建模的深度高效连续流形学习

Deep Efficient Continuous Manifold Learning for Time Series Modeling

Korea University(高丽大学)

Seungwoo Jeong, Wonjun Ko, Ahmad Wisnu Mulyadi, Heung-Il Suk

AI总结:

针对对称正定矩阵结合深度学习时优化难、计算成本高的问题,提出基于微分同胚映射的高效深度连续流形学习框架,整合流形常微分方程与门控循环网络,在多类时间序列任务上性能优于现有方法。

摘要:

随着深度神经网络在各领域取得前所未有的成功,非欧数据建模正受到广泛关注。其中,对称正定矩阵因能学习有效的统计表征,在计算机视觉、信号处理与医学图像分析领域得到了积极研究。然而,受其严格约束限制,对称正定矩阵的优化问题仍具挑战性且计算成本较高,尤其是在与深度学习框架结合时问题更突出。本文提出一种利用黎曼流形与Cholesky空间之间微分同胚映射的框架,该框架不仅能高效求解优化问题,还可大幅降低计算成本。此外,针对时间序列数据的动态建模,我们通过系统整合流形常微分方程与门控循环神经网络,设计了一种连续流形学习方法。值得注意的是,由于Cholesky空间中矩阵具有良好的参数化特性,训练配备黎曼几何度量的所提网络十分简便。我们在规则与不规则时间序列数据集上开展的实验表明,所提模型可高效可靠地训练,在各类时间序列任务上的表现优于现有流形方法与当前最优(SOTA)方法。

英文摘要:

Modeling non-Euclidean data is drawing extensive attention along with the unprecedented successes of deep neural networks in diverse fields. Particularly, a symmetric positive definite matrix is being actively studied in computer vision, signal processing, and medical image analysis, due to its ability to learn beneficial statistical representations. However, owing to its rigid constraints, it remains challenging to optimization problems and inefficient computational costs, especially, when incorporating it with a deep learning framework. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifolds and a Cholesky space, by which it becomes feasible not only to efficiently solve optimization problems but also to greatly reduce computation costs. Further, for dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network. It is worth noting that due to the nice parameterization of matrices in a Cholesky space, training our proposed network equipped with Riemannian geometric metrics is straightforward. We demonstrate through experiments over regular and irregular time-series datasets that our proposed model can be efficiently and reliably trained and outperforms existing manifold methods and state-of-the-art methods in various time-series tasks.

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。

↑