Graph Neural Networks for Model Recommendation using Time Series Data

Aleksandr Pletnev, Rodrigo Rivera-Castro, Evgeny Burnaev

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Time series prediction aims to predict future values to help stakeholders make proper strategic decisions. This problem is relevant in all industries and areas, ranging from financial data to demand to forecast. However, it remains challenging for practitioners to select the appropriate model to use for forecasting tasks. With this in mind, we present a model architecture based on Graph Neural Networks to provide model recommendations for time series forecasting. We validate our approach on three relevant datasets and compare it against more than sixteen techniques. Our study shows that the proposed method performs better than target baselines and state of the art, including meta-learning. The results show the relevancy and suitability of GNN as methods for model recommendations in time series forecasting.

    Original languageEnglish
    Title of host publicationProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
    EditorsM. Arif Wani, Feng Luo, Xiaolin Li, Dejing Dou, Francesco Bonchi
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1534-1541
    Number of pages8
    ISBN (Electronic)9781728184708
    DOIs
    Publication statusPublished - Dec 2020
    Event19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020 - Virtual, Miami, United States
    Duration: 14 Dec 202017 Dec 2020

    Publication series

    NameProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020

    Conference

    Conference19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
    Country/TerritoryUnited States
    CityVirtual, Miami
    Period14/12/2017/12/20

    Keywords

    • Graph Neural Network
    • Model Recommendation
    • Time Series

    Fingerprint

    Dive into the research topics of 'Graph Neural Networks for Model Recommendation using Time Series Data'. Together they form a unique fingerprint.

    Cite this