Multivariate Time Series Forecasting with Latent Graph Inference

This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Satorras, Victor Garcia, Rangapuram, Syama Sundar, Januschowski, Tim
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Satorras, Victor Garcia
Rangapuram, Syama Sundar
Januschowski, Tim
description This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.
doi_str_mv 10.48550/arxiv.2203.03423
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2203_03423</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2203_03423</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-7b4bda77623628ded706183f45f6e1ecd1b4d5e5e06eb90ac75b176f87e904e3</originalsourceid><addsrcrecordid>eNotz71uwjAYhWEvDBVwAZ3qG0jqf4eNChWKlKoD7NHn-DNYghQ55u_uKdDpLK-O9BDyylmpKq3ZO6RLPJVCMFkyqYR8IdPv4y7HE6QIGek67pGuMEXs6fw3YQt9jt2GnmPe0vqv6DJdJDhs6bILmLBrcUQGAXY9jv93SFbzz_Xsq6h_FsvZR12AsbKwTjkP1hohjag8essMr2RQOhjk2HrulNeokRl0Ewat1Y5bEyqLE6ZQDsnb8_UhaA4p7iFdm7ukeUjkDdk4Q6U</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multivariate Time Series Forecasting with Latent Graph Inference</title><source>arXiv.org</source><creator>Satorras, Victor Garcia ; Rangapuram, Syama Sundar ; Januschowski, Tim</creator><creatorcontrib>Satorras, Victor Garcia ; Rangapuram, Syama Sundar ; Januschowski, Tim</creatorcontrib><description>This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.</description><identifier>DOI: 10.48550/arxiv.2203.03423</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2022-03</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2203.03423$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2203.03423$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Satorras, Victor Garcia</creatorcontrib><creatorcontrib>Rangapuram, Syama Sundar</creatorcontrib><creatorcontrib>Januschowski, Tim</creatorcontrib><title>Multivariate Time Series Forecasting with Latent Graph Inference</title><description>This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71uwjAYhWEvDBVwAZ3qG0jqf4eNChWKlKoD7NHn-DNYghQ55u_uKdDpLK-O9BDyylmpKq3ZO6RLPJVCMFkyqYR8IdPv4y7HE6QIGek67pGuMEXs6fw3YQt9jt2GnmPe0vqv6DJdJDhs6bILmLBrcUQGAXY9jv93SFbzz_Xsq6h_FsvZR12AsbKwTjkP1hohjag8essMr2RQOhjk2HrulNeokRl0Ewat1Y5bEyqLE6ZQDsnb8_UhaA4p7iFdm7ukeUjkDdk4Q6U</recordid><startdate>20220307</startdate><enddate>20220307</enddate><creator>Satorras, Victor Garcia</creator><creator>Rangapuram, Syama Sundar</creator><creator>Januschowski, Tim</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220307</creationdate><title>Multivariate Time Series Forecasting with Latent Graph Inference</title><author>Satorras, Victor Garcia ; Rangapuram, Syama Sundar ; Januschowski, Tim</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-7b4bda77623628ded706183f45f6e1ecd1b4d5e5e06eb90ac75b176f87e904e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Satorras, Victor Garcia</creatorcontrib><creatorcontrib>Rangapuram, Syama Sundar</creatorcontrib><creatorcontrib>Januschowski, Tim</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Satorras, Victor Garcia</au><au>Rangapuram, Syama Sundar</au><au>Januschowski, Tim</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multivariate Time Series Forecasting with Latent Graph Inference</atitle><date>2022-03-07</date><risdate>2022</risdate><abstract>This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.</abstract><doi>10.48550/arxiv.2203.03423</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2203.03423
ispartof
issn
language eng
recordid cdi_arxiv_primary_2203_03423
source arXiv.org
subjects Computer Science - Learning
title Multivariate Time Series Forecasting with Latent Graph Inference
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-20T20%3A48%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multivariate%20Time%20Series%20Forecasting%20with%20Latent%20Graph%20Inference&rft.au=Satorras,%20Victor%20Garcia&rft.date=2022-03-07&rft_id=info:doi/10.48550/arxiv.2203.03423&rft_dat=%3Carxiv_GOX%3E2203_03423%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true