Deep Efficient Continuous Manifold Learning for Time Series Modeling
- 28 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 171-184
Abstract
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.Keywords
All Related Versions
Funding Information
- Institute of Information and communications Technology Planning & Evaluation (2022-0-00959)
- Few-Shot Learning of Causal Inference in Vision and Language for Decision Making (2019-0-00079)
- Korea University (2017-0-00451)
- Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions
This publication has 52 references indexed in Scilit:
- FairMOT: On the Fairness of Detection and Re-identification in Multiple Object TrackingInternational Journal of Computer Vision, 2021
- Multi-Scale Neural Network for EEG Representation Learning in BCIIEEE Computational Intelligence Magazine, 2021
- XSleepNet: Multi-View Sequential Model for Automatic Sleep StagingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Predicting Alzheimer's disease progression using deep recurrent neural networksNeuroImage, 2020
- Intra- and inter-epoch temporal context network (IITNet) using sub-epoch features for automatic sleep scoring on raw single-channel EEGBiomedical Signal Processing and Control, 2020
- SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep StagingIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019
- Joint Classification and Prediction CNN Framework for Automatic Sleep Stage ClassificationIEEE Transactions on Biomedical Engineering, 2018
- Estimating Missing Data in Temporal Data Streams Using Multi-Directional Recurrent Neural NetworksIEEE Transactions on Biomedical Engineering, 2018
- Recurrent Neural Networks for Multivariate Time Series with Missing ValuesScientific Reports, 2018
- DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEGIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017