paper-with-me

Papers

Learnable Path in Neural Controlled Differential Equations

2023-01-11 · Sheo Yon Jhin, Minju Jo, Seungji Kook, Noseong Park, Sungpil Woo, Sunhwan Lim

Neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neural networks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e.g., neural ordinary differential equations (NODEs), the key distinctive characteristics of NCDEs are i) the adoption of the continuous path created by an interpolation algorithm from each raw discrete time-series sample and ii) the adoption of the Riemann--Stieltjes integral. It is the continuous path which makes NCDEs be analogues to continuous RNNs. However, NCDEs use existing interpolation algorithms to create the path, which is unclear whether they can create an optimal path. To this end, we present a method to generate another latent path (rather than relying on existing interpolation algorithms), which is identical to learning an appropriate interpolation method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it. Our method shows the best performance in both time-series classification and forecasting.

📄 PDF Abstract BibTeX arXiv:2301.04333

Code (2)

alflsowl12/LEAP 공식 구현 pytorch
jeongwhanchoi/LEAP 공식 구현 pytorch

Tasks

DecoderIrregular Time SeriesTime SeriesTime Series AnalysisTime Series Classification

Similar Papers 제목 키워드 기반

Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

2026-02-02 · Egor Serov, Ilya Kuleshov, Alexey Zaytsev arxiv

Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the driving control path often restricts their efficiency. Standard splines …

Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference

2024-02-28 · Benjamin Walker, Andrew D. McLeod, Tiexin Qin, Yichuan Cheng 외

The vector field of a controlled differential equation (CDE) describes the relationship between a control path and the evolution of a solution path. Neural CDEs (NCDEs) treat time series data as observations from a contr…

MambaTime SeriesTime Series Classification

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning

2025-06-25 · Torben Berndt, Benjamin Walker, Tiexin Qin, Jan Stühmer 외

Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfu…

Graph Representation LearningRepresentation Learning

EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting

2022-04-19 · Sheo Yon Jhin, Jaehoon Lee, Minju Jo, Seungji Kook 외

Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks. Among them, time-series modeling with neural controlled differe…

BIG-bench Machine LearningDecoderIrregular Time SeriesTime Series+2

Universal Time Series Generation with Neural Controlled Differential Equations

2026-05-27 · Torben Berndt, Elyes Farjallah, Leif Seute, Raeid Saqur 외 arxiv

Recent work on the sequence universality of State Space Models (SSMs) has introduced efficient, maximally expressive continuous-time approaches for time-series modelling. While these works focus on discriminative setting…