Continuous Product Graph Neural Networks
- URL: http://arxiv.org/abs/2405.18877v1
- Date: Wed, 29 May 2024 08:36:09 GMT
- Title: Continuous Product Graph Neural Networks
- Authors: Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo,
- Abstract summary: Multidomain data defined on multiple graphs holds significant potential in practical applications in computer science.
We introduce Continuous Product Graph Neural Networks (CITRUS) that emerge as a natural solution to the TPDEG.
We evaluate CITRUS on well-known traffic and weather forecasting datasets, demonstrating superior performance over existing approaches.
- Score: 5.703629317205571
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Processing multidomain data defined on multiple graphs holds significant potential in various practical applications in computer science. However, current methods are mostly limited to discrete graph filtering operations. Tensorial partial differential equations on graphs (TPDEGs) provide a principled framework for modeling structured data across multiple interacting graphs, addressing the limitations of the existing discrete methodologies. In this paper, we introduce Continuous Product Graph Neural Networks (CITRUS) that emerge as a natural solution to the TPDEG. CITRUS leverages the separability of continuous heat kernels from Cartesian graph products to efficiently implement graph spectral decomposition. We conduct thorough theoretical analyses of the stability and over-smoothing properties of CITRUS in response to domain-specific graph perturbations and graph spectra effects on the performance. We evaluate CITRUS on well-known traffic and weather spatiotemporal forecasting datasets, demonstrating superior performance over existing approaches.
Related papers
- Dynamic Causal Explanation Based Diffusion-Variational Graph Neural
Network for Spatio-temporal Forecasting [60.03169701753824]
We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting.
The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
arXiv Detail & Related papers (2023-05-16T11:38:19Z) - EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph
Learning [114.72818205974285]
This paper aims to design an easy-to-use pipeline (termed as EasyDGL) composed of three key modules with both strong ability fitting and interpretability.
EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
arXiv Detail & Related papers (2023-03-22T06:35:08Z) - Latent Graph Inference using Product Manifolds [0.0]
We generalize the discrete Differentiable Graph Module (dDGM) for latent graph learning.
Our novel approach is tested on a wide range of datasets, and outperforms the original dDGM model.
arXiv Detail & Related papers (2022-11-26T22:13:06Z) - Robust Causal Graph Representation Learning against Confounding Effects [21.380907101361643]
We propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects.
RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders.
arXiv Detail & Related papers (2022-08-18T01:31:25Z) - Sparse Graph Learning from Spatiotemporal Time Series [16.427698929775023]
We propose a graph learning framework that learns the relational dependencies as distributions over graphs.
We show that the proposed solution can be used as a stand-alone graph identification procedure as well as a graph learning component of an end-to-end forecasting architecture.
arXiv Detail & Related papers (2022-05-26T17:02:43Z) - Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem.
In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN)
GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
arXiv Detail & Related papers (2022-05-19T14:08:15Z) - 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) - Score-based Generative Modeling of Graphs via the System of Stochastic
Differential Equations [57.15855198512551]
We propose a novel score-based generative model for graphs with a continuous-time framework.
We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
arXiv Detail & Related papers (2022-02-05T08:21:04Z) - 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) - A continuum limit for the PageRank algorithm [1.2891210250935146]
Semi-supervised and unsupervised machine learning methods often rely on graphs to model data.
We propose a new framework for rigorously studying continuum limits of learning algorithms on directed graphs.
We show how it can be interpreted as a numerical scheme on a directed graph involving a type of normalized graph Laplacian.
arXiv Detail & Related papers (2020-01-24T12:56:09Z)
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.