AI Paper Atlas

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

TPAMI 2023 · Time series › Causal and generative time series · approach: Neural differential equations · 22 citations (OpenAlex)

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 changedWhereMeasuredEffect
add manifold ODE (ODEFunc) to RGRU (ablation)ODE-RGRU · SleepEDF-20 (EEG)accuracy: 84.1 -> 86.3Improved
add manifold ODE (ODEFunc) to RGRU (ablation)ODE-RGRU · SleepEDF-20 (EEG/EOG)accuracy: 84.3 -> 86.6Improved
add manifold ODE (ODEFunc) to RGRU (ablation)ODE-RGRU · SleepEDF-20 (EEG)macro F1: 74 -> 80.2Improved
add manifold ODE (ODEFunc) to RGRU (ablation)ODE-RGRU · SleepEDF-20 (EEG/EOG)macro F1: 74.8 -> 80.3Improved
Cholesky-space manifold GRU instead of Euclidean GRU/LSTMGRU · UCF11accuracy: 79.3 -> 89.4Improved
manifold ODE-RGRU instead of ManifoldDCNNManifoldDCNN · UCF11accuracy: 82.3 -> 89.4Improved
ODE-RGRU versus XSleepNet using raw signals and spectrogramsXSleepNet · SleepEDF-20 (EEG/EOG)accuracy: 86.4 -> 86.6Mixed
ODE-RGRU versus Neural CDE with 50% data droppedNeural CDE · Irregular CharacterTrajectoriesaccuracy: 98.8 -> 98.3Hurt
ODE-RGRU versus ODE-RNN with 30% data droppedODE-RNN · Irregular CharacterTrajectoriesaccuracy: 95.4 -> 98.9Improved
ODE-RGRU versus TS2Vec for long-horizon forecastingTS2Vec · ETTh1 (H=720)MSE: 1.048 -> 0.862Improved
ODE-RGRU versus TS2Vec for short-horizon forecastingTS2Vec · ETTh2 (H=24)MSE: 0.398 -> 0.781Hurt
ODE-RGRU versus MinimalRNN for imputationMinimalRNN · TADPOLE ADAS-cog13R2: 0.635 -> 0.726Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy