INDEQS: Informed Neural controlled Differential EQuationS
- URL: http://arxiv.org/abs/2606.19138v1
- Date: Wed, 17 Jun 2026 14:46:23 GMT
- Title: INDEQS: Informed Neural controlled Differential EQuationS
- Abstract summary: We introduce Informed Informed Neural controlled Differential EQuationS (INDEQS), a graph-based NCDE forecasting method.<n>INDEQS separates inner mixing of hidden states across graph nodes from outer mixing between vector field and control.<n>We evaluate INDEQS on two real-world tasks: river discharge forecasting on a hydrological network and traffic flow prediction on PeMS08.
- Score: 13.60302952986747
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Neural Controlled Differential Equations (NCDE) provide a powerful continuous-time framework for forecasting time series, but standard graph-based extensions typically learn spatial structure purely from data, even in settings where a directed graph structure is known a priori. We introduce Informed Neural controlled Differential EQuationS (INDEQS), a graph-based NCDE forecasting method that incorporates prior knowledge of a directed graph at distinct architectural positions. INDEQS separates inner mixing of hidden states across graph nodes from outer mixing between vector field and control, and offers both a lightweight graph-constrained variant and a more expressive variant, learning additional graph connections from data via adaptive graph convolutions. To systematically study when graph informedness is beneficial in forecasting, we devise a continuous advection simulation on directed graphs, yielding synthetic spatio-temporal datasets with known ground-truth flow structure. We then evaluate INDEQS on two real-world tasks: river discharge forecasting on a hydrological network and traffic flow prediction on PeMS08. Across these synthetic and real-world benchmarks, outer informedness consistently improves mean absolute error over an uninformed NCDE with comparable parameter count, particularly on larger graphs, while inner informedness offers a more parameter-efficient alternative when strict adherence to a known adjacency is desired. A comparison of discrete convolutional and continuous-time decoders further shows that continuous decoders yield better accuracy and greater temporal flexibility on real-world tasks. An implementation of INDEQS and the advection simulation is available at https://github.com/Mitchi1/indeqs.
Related papers
- Graph Signal Generative Diffusion Models [74.75869068073577]
We introduce U-shaped encoder-decoder graph neural networks (U-GNNs) for graph signal generation using denoising diffusion processes.<n>The architecture learns node features at different resolutions with skip connections between the encoder and decoder paths.<n>We demonstrate the effectiveness of the diffusion model in probabilistic forecasting of stock prices.
arXiv Detail & Related papers (2025-09-21T21:57:27Z) - Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations [1.2584276673531931]
Graph Neural Networks have achieved impressive results across diverse network modeling tasks, but accurately estimating uncertainty on graphs remains difficult.<n>We present a principled way to design a novel message passing scheme that incorporates spatial-temporal noises motivated by the Gaussian Process approach to SPDE.<n>Our method simultaneously captures uncertainty across space and time and allows explicit control over the covariance kernel smoothness, thereby enhancing uncertainty estimates on graphs with both low and high label informativeness.
arXiv Detail & Related papers (2025-06-07T19:58:38Z) - Adaptive Sparsified Graph Learning Framework for Vessel Behavior Anomalies [3.3711670942444014]
Graph neural networks have emerged as a powerful tool for learning precise interactions.<n>Our method introduces an innovative graph representation where edges are modeled as timestamp nodes.<n>This setup is extended to construct a multi-ship graph that captures spatial interactions while preserving graph sparsity.
arXiv Detail & Related papers (2025-02-20T02:01:40Z) - FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure
Graph Perspective [48.00240550685946]
Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively.
We propose a novel Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space.
Our experiments on seven datasets have demonstrated superior performance with higher efficiency and fewer parameters compared with state-of-the-
arXiv Detail & Related papers (2023-11-10T17:13:26Z) - Space-Time Graph Neural Networks with Stochastic Graph Perturbations [100.31591011966603]
Space-time graph neural networks (ST-GNNs) learn efficient graph representations of time-varying data.
In this paper we revisit the properties of ST-GNNs and prove that they are stable to graph stabilitys.
Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs.
arXiv Detail & Related papers (2022-10-28T16:59:51Z) - Spatial-Temporal Adaptive Graph Convolution with Attention Network for
Traffic Forecasting [4.1700160312787125]
We propose a novel network, Spatial-Temporal Adaptive graph convolution with Attention Network (STAAN) for traffic forecasting.
Firstly, we adopt an adaptive dependency matrix instead of using a pre-defined matrix during GCN processing to infer the inter-dependencies among nodes.
Secondly, we integrate PW-attention based on graph attention network which is designed for global dependency, and GCN as spatial block.
arXiv Detail & Related papers (2022-06-07T09:08:35Z) - Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes.
We propose a metric that quantifies the ability of a graph to mix the current gradients.
Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
arXiv Detail & Related papers (2022-04-13T15:54:35Z) - Spatio-Temporal Latent Graph Structure Learning for Traffic Forecasting [6.428566223253948]
We propose a new traffic forecasting framework--S-Temporal Latent Graph Structure Learning networks (ST-LGSL)
The model employs a graph based on Multilayer perceptron and K-Nearest Neighbor, which learns the latent graph topological information from the entire data.
With the dependencies-kNN based on ground-truth adjacency matrix and similarity metric in kNN, ST-LGSL aggregates the top focusing on geography and node similarity.
arXiv Detail & Related papers (2022-02-25T10:02:49Z) - Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE)
Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures.
Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
arXiv Detail & Related papers (2022-02-17T02:17:31Z) - Block-Approximated Exponential Random Graphs [77.4792558024487]
An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs.
We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions.
Our methods are scalable to sparse graphs consisting of millions of nodes.
arXiv Detail & Related papers (2020-02-14T11:42:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.