A Study of Joint Graph Inference and Forecasting

• URL: http://arxiv.org/abs/2109.04979v1
• Date: Fri, 10 Sep 2021 16:34:35 GMT
• Title: A Study of Joint Graph Inference and Forecasting
• Authors: Daniel Z\"ugner, Fran\c{c}ois-Xavier Aubet, Victor Garcia Satorras, Tim Januschowski, Stephan G\"unnemann, Jan Gasthaus
• Abstract summary: We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series. By parameterizing a graph in a differentiable way, the models aim to improve forecasting quality.
• Score: 13.340967777671565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series. The core assumption behind these models is that there is a latent graph between the time series (nodes) that governs the evolution of the multivariate time series. By parameterizing a graph in a differentiable way, the models aim to improve forecasting quality. We compare four recent models of this class on the forecasting task. Further, we perform ablations to study their behavior under changing conditions, e.g., when disabling the graph-learning modules and providing the ground-truth relations instead. Based on our findings, we propose novel ways of combining the existing architectures.

Related papers

• A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation [59.14165404728197]
  We provide an up-to-date and forward-looking review of deep graph learning under distribution shifts. Specifically, we cover three primary scenarios: graph OOD generalization, training-time graph OOD adaptation, and test-time graph OOD adaptation. To provide a better understanding of the literature, we systematically categorize the existing models based on our proposed taxonomy.
  arXiv  Detail & Related papers  (2024-10-25T02:39:56Z)
• Sparsity exploitation via discovering graphical models in multi-variate time-series forecasting [1.2762298148425795]
  We propose a decoupled training method, which includes a graph generating module and a GNNs forecasting module. First, we use Graphical Lasso (or GraphLASSO) to directly exploit the sparsity pattern from data to build graph structures. Second, we fit these graph structures and the input data into a Graph Convolutional Recurrent Network (GCRN) to train a forecasting model.
  arXiv  Detail & Related papers  (2023-06-29T16:48:00Z)
• Temporal Graph Neural Networks for Irregular Data [14.653008985229615]
  TGNN4I model is designed to handle both irregular time steps and partial observations of the graph. Time-continuous dynamics enables the model to make predictions at arbitrary time steps. Experiments on simulated data and real-world data from traffic and climate modeling validate the usefulness of both the graph structure and time-continuous dynamics.
  arXiv  Detail & Related papers  (2023-02-16T16:47:55Z)
• Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting [50.901984244738806]
  We show how to model the evolutionary and multi-scale interactions of time series. In particular, we first provide a hierarchical graph structure cooperated with the dilated convolution to capture the scale-specific correlations. A unified neural network is provided to integrate the components above to get the final prediction.
  arXiv  Detail & Related papers  (2022-06-28T08:11:12Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• 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)
• Learning Sparse and Continuous Graph Structures for Multivariate Time Series Forecasting [5.359968374560132]
  Learning Sparse and Continuous Graphs for Forecasting (LSCGF) is a novel deep learning model that joins graph learning and forecasting. In this paper, we propose a brand new method named Smooth Sparse Unit (SSU) to learn sparse and continuous graph adjacency matrix. Our model achieves state-of-the-art performances with minor trainable parameters.
  arXiv  Detail & Related papers  (2022-01-24T13:35:37Z)
• Discrete Graph Structure Learning for Forecasting Multiple Time Series [14.459541930646205]
  Time series forecasting is an extensively studied subject in statistics, economics, and computer science. In this work, we propose learning the structure simultaneously with a graph neural network (GNN) if the graph is unknown. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning.
  arXiv  Detail & Related papers  (2021-01-18T03:36:33Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)
• Permutation Invariant Graph Generation via Score-Based Generative Modeling [114.12935776726606]
  We propose a permutation invariant approach to modeling graphs, using the recent framework of score-based generative modeling. In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph. For graph generation, we find that our learning approach achieves better or comparable results to existing models on benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-02T03:06:14Z)

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.