Research map / Time series / Causal and generative time series
Deep Efficient Continuous Manifold Learning for Time Series Modeling
Seungwoo Jeong, Wonjun Ko, Ahmad Wisnu Mulyadi, Heung‐Il Suk
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add manifold ODE (ODEFunc) to RGRU (ablation) | ODE-RGRU · SleepEDF-20 (EEG) | accuracy: 84.1 -> 86.3 | Improved |
| add manifold ODE (ODEFunc) to RGRU (ablation) | ODE-RGRU · SleepEDF-20 (EEG/EOG) | accuracy: 84.3 -> 86.6 | Improved |
| add manifold ODE (ODEFunc) to RGRU (ablation) | ODE-RGRU · SleepEDF-20 (EEG) | macro F1: 74 -> 80.2 | Improved |
| add manifold ODE (ODEFunc) to RGRU (ablation) | ODE-RGRU · SleepEDF-20 (EEG/EOG) | macro F1: 74.8 -> 80.3 | Improved |
| Cholesky-space manifold GRU instead of Euclidean GRU/LSTM | GRU · UCF11 | accuracy: 79.3 -> 89.4 | Improved |
| manifold ODE-RGRU instead of ManifoldDCNN | ManifoldDCNN · UCF11 | accuracy: 82.3 -> 89.4 | Improved |
| ODE-RGRU versus XSleepNet using raw signals and spectrograms | XSleepNet · SleepEDF-20 (EEG/EOG) | accuracy: 86.4 -> 86.6 | Mixed |
| ODE-RGRU versus Neural CDE with 50% data dropped | Neural CDE · Irregular CharacterTrajectories | accuracy: 98.8 -> 98.3 | Hurt |
| ODE-RGRU versus ODE-RNN with 30% data dropped | ODE-RNN · Irregular CharacterTrajectories | accuracy: 95.4 -> 98.9 | Improved |
| ODE-RGRU versus TS2Vec for long-horizon forecasting | TS2Vec · ETTh1 (H=720) | MSE: 1.048 -> 0.862 | Improved |
| ODE-RGRU versus TS2Vec for short-horizon forecasting | TS2Vec · ETTh2 (H=24) | MSE: 0.398 -> 0.781 | Hurt |
| ODE-RGRU versus MinimalRNN for imputation | MinimalRNN · TADPOLE ADAS-cog13 | R2: 0.635 -> 0.726 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ShapeNet — ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification (AAAI 2021) · better on 2 of 2 shared results
- TS2Vec — TS2Vec: Towards Universal Representation of Time Series (AAAI 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Building Transformation Layers for Riemannian Neural Networks (NeurIPS 2026 · similarity 0.87)
- RMLR: Extending Multinomial Logistic Regression into General Geometries (NeurIPS 2024 · similarity 0.87)
- Matrix Manifold Neural Networks++ (ICLR 2024 · similarity 0.87)
- Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning (ICLR 2025 · similarity 0.87)
- Residual Deep Gaussian Processes on Manifolds (ICLR 2025 · similarity 0.86)
- Riemannian Multinomial Logistics Regression for SPD Neural Networks (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
