Graph Deep Factors for Forecasting

Abstract

Deep probabilistic forecasting techniques have recently been proposed for modeling large collections of time-series. However, these techniques explicitly assume either complete independence (local model) or complete dependence (global model) between time-series in the collection. This corresponds to the two extreme cases where every time-series is disconnected from every other time-series in the collection or likewise, that every time-series is related to every other time-series resulting in a completely connected graph. In this work, we propose a deep hybrid probabilistic graph-based forecasting framework called Graph Deep Factors (GraphDF) that goes beyond these two extremes by allowing nodes and their time-series to be connected to others in an arbitrary fashion. GraphDF is a hybrid forecasting framework that consists of a relational global and relational local model. In particular, we propose a relational global model that learns complex non-linear time-series patterns globally using the structure of the graph to improve both forecasting accuracy and computational efficiency. Similarly, instead of modeling every time-series independently, we learn a relational local model that not only considers its individual time-series but also the time-series of nodes that are connected in the graph. The experiments demonstrate the effectiveness of the proposed deep hybrid graph-based forecasting model compared to the state-of-the-art methods in terms of its forecasting accuracy, runtime, and scalability. Our case study reveals that GraphDF can successfully generate cloud usage forecasts and opportunistically schedule workloads to increase cloud cluster utilization by 47.5% on average.

arXiv comment18 pages, 7 figures, submitted to MLSys 2021

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• A Multi-Horizon Quantile Recurrent Forecaster
• Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting
• GluonTS: Probabilistic Time Series Models in Python
• Deep Factors for Forecasting
• Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data
• Deep Factors with Gaussian Processes for Forecasting
• Prediction Under Uncertainty with Error-Encoding Networks