AI Paper Atlas

Research map / Time series / Causal and generative time series

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

YongKyung Oh, Dong-Young Lim, Sungil Kim

AAAI 2026 · Time series › Causal and generative time series · approach: Neural differential equations · 0 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
replace the fixed spline path in Neural CDE with a learned non-invertible MLP pathNeural CDE · 18 UEA/UCR datasets (average)accuracy: 0.667 -> 0.689Improved
make the learned control path an invertible flow instead of an MLP (ablation)Neural CDE with learned path · 18 UEA/UCR datasets (average)accuracy: 0.689 -> 0.730Improved
make the learned path invertible instead of an MLP, at 70% missing (ablation)Neural CDE with learned path · 18 UEA/UCR datasets (70% missing)accuracy: 0.655 -> 0.718Improved
use a fixed spline path versus FlowPath's learned invertible path under 70% missing dataNeural CDE · 18 UEA/UCR datasets (70% missing)accuracy: 0.652 -> 0.718Improved
use the per-dataset best flow versus a fixed ResNet flow (ablation)FlowPath · 18 UEA/UCR datasets (average)accuracy: 0.705 -> 0.730Mixed
FlowPath versus strongest baseline DualDynamics, pairwise over dataset-scenariosDualDynamics · 18 UEA/UCR datasets (all settings)wins/ties/losses: 40 wins, 6 ties, 26 lossesImproved
FlowPath versus DualDynamics with no missing dataDualDynamics · 18 UEA/UCR datasets (regular)wins/ties/losses: 8 wins, 2 ties, 8 lossesNo clear effect
use GRU flow instead of spline path in Neural CDE on PAMAP2 without sensor dropoutNeural CDE · PAMAP2 (0% sensor dropout)F1 score: 95.0 -> 95.6Improved
use ResNet flow instead of spline path at 50% sensor dropoutNeural CDE · PAMAP2 (50% sensor dropout)F1 score: 51.6 -> 57.9Improved
use a learned MLP path instead of spline in Neural CDE on PAMAP2 without dropout (ablation)Neural CDE · PAMAP2 (0% sensor dropout)F1 score: 95.0 -> 93.9Hurt
choose ResNet flow over GRU flow at heavy sensor dropout (ablation)FlowPath · PAMAP2 (40% sensor dropout)F1 score: 59.6 -> 65.9Improved
use FlowPath instead of Neural CDE under 30% sensor dropout on PAMAP2Neural CDE · PAMAP2 (30% sensor dropout)accuracy: 65.5 -> 67.3Improved

Later papers that compared with this method

1 later accepted paper reports FlowPath as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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