GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecasting

• URL: http://arxiv.org/abs/2307.03595v1
• Date: Fri, 7 Jul 2023 13:38:16 GMT
• Title: GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecasting
• Authors: Sitan Yang, Malcolm Wolff, Shankar Ramasubramanian, Vincent Quenneville-Belair, Ronak Metha, Michael W. Mahoney
• Abstract summary: A rapidly growing topic of interest is forecasting time series which lack sufficient historical data. We introduce a novel yet simple method to address this problem by leveraging graph neural networks (GNNs) as a data augmentation. We show that our architecture can use either data-driven or domain knowledge-defined graphs, scaling to incorporate information from multiple very large graphs with millions of nodes.
• Score: 36.85187795776383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Encoder-decoder deep neural networks have been increasingly studied for multi-horizon time series forecasting, especially in real-world applications. However, to forecast accurately, these sophisticated models typically rely on a large number of time series examples with substantial history. A rapidly growing topic of interest is forecasting time series which lack sufficient historical data -- often referred to as the ``cold start'' problem. In this paper, we introduce a novel yet simple method to address this problem by leveraging graph neural networks (GNNs) as a data augmentation for enhancing the encoder used by such forecasters. These GNN-based features can capture complex inter-series relationships, and their generation process can be optimized end-to-end with the forecasting task. We show that our architecture can use either data-driven or domain knowledge-defined graphs, scaling to incorporate information from multiple very large graphs with millions of nodes. In our target application of demand forecasting for a large e-commerce retailer, we demonstrate on both a small dataset of 100K products and a large dataset with over 2 million products that our method improves overall performance over competitive baseline models. More importantly, we show that it brings substantially more gains to ``cold start'' products such as those newly launched or recently out-of-stock.

Related papers

• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data [65.6499834212641]
  We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm. By considering domain similarities through task-specific metadata, our model improved generalization, where the excess risk decreases as the number of training tasks increases. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
  arXiv  Detail & Related papers  (2024-06-23T21:28:50Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  We present a Masked-based Universal Time Series Forecasting Transformer (Moirai) Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains. Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• 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)
• Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain [54.67888148566323]
  We introduce three large-scale time series forecasting datasets from the cloud operations domain. We show it is a strong zero-shot baseline and benefits from further scaling, both in model and dataset size. Accompanying these datasets and results is a suite of comprehensive benchmark results comparing classical and deep learning baselines to our pre-trained method.
  arXiv  Detail & Related papers  (2023-10-08T08:09:51Z)
• TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting [20.03223916749058]
  Time series forecasting lies at the core of important real-world applications in science and engineering. We propose TimeGNN, a method that learns dynamic temporal graph representations. TimeGNN achieves inference times 4 to 80 times faster than other state-of-the-art graph-based methods.
  arXiv  Detail & Related papers  (2023-07-27T08:10:19Z)
• HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting [13.49661832917228]
  We make the first attempt to explore long-term traffic forecasting, e.g., 1-day forecasting. We propose a novel Hierarchical U-net TransFormer to address the issues of long-term traffic forecasting. The proposed HUTFormer significantly outperforms state-of-the-art traffic forecasting and long time series forecasting baselines.
  arXiv  Detail & Related papers  (2023-07-27T02:43:21Z)
• 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)
• Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting [13.441945545904504]
  We propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP) Specifically, we design a pre-training model to efficiently learn temporal patterns from very long-term history time series. Our framework is capable of significantly enhancing downstream STGNNs, and our pre-training model aptly captures temporal patterns.
  arXiv  Detail & Related papers  (2022-06-18T04:24:36Z)
• Multivariate Time Series Regression with Graph Neural Networks [0.6124773188525718]
  Recent advances in adapting Deep Learning to graphs have shown promising potential in various graph-related tasks. However, these methods have not been adapted for time series related tasks to a great extent. In this work, we propose an architecture capable of processing these long sequences in a multivariate time series regression task.
  arXiv  Detail & Related papers  (2022-01-03T16:11:46Z)

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.