mlsanityData to 14 Oct 2026

Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series

arXiv 2410.14030 ↗First posted 17 Oct 2024cs.LG cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

Interacting systems are prevalent in nature. It is challenging to accurately predict the dynamics of the system if its constituent components are analyzed independently. We develop a graph-based model that unveils the systemic interactions of time series observed at irregular time points, by using a directed acyclic graph to model the conditional dependencies (a form of causal notation) of the system components and learning this graph in tandem with a continuous-time model that parameterizes the solution curves of ordinary differential equations (ODEs). Our technique, a graph neural flow, leads to substantial enhancements over non-graph-based methods, as well as graph-based methods without the modeling of conditional dependencies. We validate our approach on several tasks, including time series classification and forecasting, to demonstrate its efficacy.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 32 of its 50 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

32 of 50 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  4. 2016Density estimation using Real NVPcited by 2,042
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  8. 2018DeepMind Control Suitecited by 956
  9. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  10. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  11. 2018Invertible Residual Networkscited by 365
  12. 2018Neural Relational Inference for Interacting Systemscited by 339
20 more
  1. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  2. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
  3. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 231
  4. 2019Latent ODEs for Irregularly-Sampled Time Seriescited by 183
  5. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  6. 2019Graph Neural Ordinary Differential Equationscited by 154
  7. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  8. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  9. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  10. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  11. 2020Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscited by 61
  12. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  13. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  14. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  15. 2020On Low Rank Directed Acyclic Graphs and Causal Structure Learningcited by 23
  16. 2023CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systemscited by 16
  17. 2015Cascading Power Outages Propagate Locally in an Influence Graph that is not the Actual Grid Topologycited by 9
  18. 2023Inferring dynamic regulatory interaction graphs from time series data with perturbationscited by 9
  19. 2024Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Modelscited by 5
  20. 2024Coordinated Multi-Neighborhood Learning on a Directed Acyclic Graphcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 10.

15 papers.

Sort:

  1. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 55
  2. 2025HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecastingcited by 15
  3. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  4. 2026Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecastingcited by 9
  5. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 8
  6. 2026TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patchingcited by 2
  7. 2025Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingnesscited by 1
  8. 2026MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMscited by 1
  9. 2026One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classificationcited by 1
  10. 2026Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Frameworkcited by 1
  11. 2026Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecastingcited by 0
  12. 2026MissHyper: Restoring Clinical Synchronicity in Missingness-Guided Hypergraph Forecastingcited by 0
3 more
  1. 2026Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functionscited by 0
  2. 2026BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecastingcited by 0
  3. 2026QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecastingcited by 0