EasyTPP: Towards Open Benchmarking Temporal Point Processes

Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xue, Siqiao, Shi, Xiaoming, Chu, Zhixuan, Wang, Yan, Hao, Hongyan, Zhou, Fan, Jiang, Caigao, Pan, Chen, Zhang, James Y, Wen, Qingsong, Zhou, Jun, Mei, Hongyuan
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 Xue, Siqiao
Shi, Xiaoming
Chu, Zhixuan
Wang, Yan
Hao, Hongyan
Zhou, Fan
Jiang, Caigao
Pan, Chen
Zhang, James Y
Wen, Qingsong
Zhou, Jun
Mei, Hongyuan
description Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. All the data and implementation can be found at https://github.com/ant-research/EasyTemporalPointProcess. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts.
doi_str_mv 10.48550/arxiv.2307.08097
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2307_08097</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307_08097</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-c32268f6b3f8196886e01009c0db4c1e5febf03f53ee12e3c7271ab63ad44c003</originalsourceid><addsrcrecordid>eNotj7FOwzAUAL10QIUPYMI_kPBsJ7ZDJ6hKQarUDN6jF-eZRm2TyEZA_57SMt12umPsXkBe2LKER4w__VcuFZgcLFTmhi1WmE6urp-4G78xdolvJxr4Cw1-d8S474cP7ug4jREPvB774ZPXcfSUEqVbNgt4SHT3zzlzryu3fMs22_X78nmToTYm80pKbYNuVbCi0tZqAgFQeejawgsqA7UBVCgVkZCkvJFGYKsVdkXhAdScPVy1l_pmiv057NT8XTSXC_ULLAxBfw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>EasyTPP: Towards Open Benchmarking Temporal Point Processes</title><source>arXiv.org</source><creator>Xue, Siqiao ; Shi, Xiaoming ; Chu, Zhixuan ; Wang, Yan ; Hao, Hongyan ; Zhou, Fan ; Jiang, Caigao ; Pan, Chen ; Zhang, James Y ; Wen, Qingsong ; Zhou, Jun ; Mei, Hongyuan</creator><creatorcontrib>Xue, Siqiao ; Shi, Xiaoming ; Chu, Zhixuan ; Wang, Yan ; Hao, Hongyan ; Zhou, Fan ; Jiang, Caigao ; Pan, Chen ; Zhang, James Y ; Wen, Qingsong ; Zhou, Jun ; Mei, Hongyuan</creatorcontrib><description>Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. All the data and implementation can be found at https://github.com/ant-research/EasyTemporalPointProcess. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts.</description><identifier>DOI: 10.48550/arxiv.2307.08097</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2023-07</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2307.08097$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2307.08097$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Xue, Siqiao</creatorcontrib><creatorcontrib>Shi, Xiaoming</creatorcontrib><creatorcontrib>Chu, Zhixuan</creatorcontrib><creatorcontrib>Wang, Yan</creatorcontrib><creatorcontrib>Hao, Hongyan</creatorcontrib><creatorcontrib>Zhou, Fan</creatorcontrib><creatorcontrib>Jiang, Caigao</creatorcontrib><creatorcontrib>Pan, Chen</creatorcontrib><creatorcontrib>Zhang, James Y</creatorcontrib><creatorcontrib>Wen, Qingsong</creatorcontrib><creatorcontrib>Zhou, Jun</creatorcontrib><creatorcontrib>Mei, Hongyuan</creatorcontrib><title>EasyTPP: Towards Open Benchmarking Temporal Point Processes</title><description>Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. All the data and implementation can be found at https://github.com/ant-research/EasyTemporalPointProcess. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7FOwzAUAL10QIUPYMI_kPBsJ7ZDJ6hKQarUDN6jF-eZRm2TyEZA_57SMt12umPsXkBe2LKER4w__VcuFZgcLFTmhi1WmE6urp-4G78xdolvJxr4Cw1-d8S474cP7ug4jREPvB774ZPXcfSUEqVbNgt4SHT3zzlzryu3fMs22_X78nmToTYm80pKbYNuVbCi0tZqAgFQeejawgsqA7UBVCgVkZCkvJFGYKsVdkXhAdScPVy1l_pmiv057NT8XTSXC_ULLAxBfw</recordid><startdate>20230716</startdate><enddate>20230716</enddate><creator>Xue, Siqiao</creator><creator>Shi, Xiaoming</creator><creator>Chu, Zhixuan</creator><creator>Wang, Yan</creator><creator>Hao, Hongyan</creator><creator>Zhou, Fan</creator><creator>Jiang, Caigao</creator><creator>Pan, Chen</creator><creator>Zhang, James Y</creator><creator>Wen, Qingsong</creator><creator>Zhou, Jun</creator><creator>Mei, Hongyuan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230716</creationdate><title>EasyTPP: Towards Open Benchmarking Temporal Point Processes</title><author>Xue, Siqiao ; Shi, Xiaoming ; Chu, Zhixuan ; Wang, Yan ; Hao, Hongyan ; Zhou, Fan ; Jiang, Caigao ; Pan, Chen ; Zhang, James Y ; Wen, Qingsong ; Zhou, Jun ; Mei, Hongyuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-c32268f6b3f8196886e01009c0db4c1e5febf03f53ee12e3c7271ab63ad44c003</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Xue, Siqiao</creatorcontrib><creatorcontrib>Shi, Xiaoming</creatorcontrib><creatorcontrib>Chu, Zhixuan</creatorcontrib><creatorcontrib>Wang, Yan</creatorcontrib><creatorcontrib>Hao, Hongyan</creatorcontrib><creatorcontrib>Zhou, Fan</creatorcontrib><creatorcontrib>Jiang, Caigao</creatorcontrib><creatorcontrib>Pan, Chen</creatorcontrib><creatorcontrib>Zhang, James Y</creatorcontrib><creatorcontrib>Wen, Qingsong</creatorcontrib><creatorcontrib>Zhou, Jun</creatorcontrib><creatorcontrib>Mei, Hongyuan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Xue, Siqiao</au><au>Shi, Xiaoming</au><au>Chu, Zhixuan</au><au>Wang, Yan</au><au>Hao, Hongyan</au><au>Zhou, Fan</au><au>Jiang, Caigao</au><au>Pan, Chen</au><au>Zhang, James Y</au><au>Wen, Qingsong</au><au>Zhou, Jun</au><au>Mei, Hongyuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EasyTPP: Towards Open Benchmarking Temporal Point Processes</atitle><date>2023-07-16</date><risdate>2023</risdate><abstract>Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. All the data and implementation can be found at https://github.com/ant-research/EasyTemporalPointProcess. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts.</abstract><doi>10.48550/arxiv.2307.08097</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2307.08097
ispartof
issn
language eng
recordid cdi_arxiv_primary_2307_08097
source arXiv.org
subjects Computer Science - Learning
title EasyTPP: Towards Open Benchmarking Temporal Point Processes
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T10%3A19%3A45IST&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=EasyTPP:%20Towards%20Open%20Benchmarking%20Temporal%20Point%20Processes&rft.au=Xue,%20Siqiao&rft.date=2023-07-16&rft_id=info:doi/10.48550/arxiv.2307.08097&rft_dat=%3Carxiv_GOX%3E2307_08097%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