@inproceedings{yamasaki-etal-2023-holistic,
title = "Holistic Prediction on a Time-Evolving Attributed Graph",
author = "Yamasaki, Shohei and
Sasaki, Yuya and
Karras, Panagiotis and
Onizuka, Makoto",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.765",
doi = "10.18653/v1/2023.acl-long.765",
pages = "13676--13694",
abstract = "Graph-based prediction is essential in NLP tasks such as temporal knowledge graph completion. A cardinal question in this field is, how to predict the future links, nodes, and attributes of a time-evolving attributed graph? Unfortunately, existing techniques assume that each link, node, and attribute prediction is independent, and fall short of predicting the appearance of new nodes that were not observed in the past. In this paper, we address two interrelated questions; (1) can we exploit task interdependence to improve prediction accuracy? and (2) can we predict new nodes with their attributes? We propose a unified framework that predicts node attributes and topology changes such as the appearance and disappearance of links and the emergence and loss of nodes. This frame-work comprises components for independent and interactive prediction and for predicting new nodes. Our experimental study using real-world data confirms that our interdependent prediction framework achieves higher accuracy than methods based on independent prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamasaki-etal-2023-holistic">
<titleInfo>
<title>Holistic Prediction on a Time-Evolving Attributed Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Yamasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuya</namePart>
<namePart type="family">Sasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panagiotis</namePart>
<namePart type="family">Karras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Onizuka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Graph-based prediction is essential in NLP tasks such as temporal knowledge graph completion. A cardinal question in this field is, how to predict the future links, nodes, and attributes of a time-evolving attributed graph? Unfortunately, existing techniques assume that each link, node, and attribute prediction is independent, and fall short of predicting the appearance of new nodes that were not observed in the past. In this paper, we address two interrelated questions; (1) can we exploit task interdependence to improve prediction accuracy? and (2) can we predict new nodes with their attributes? We propose a unified framework that predicts node attributes and topology changes such as the appearance and disappearance of links and the emergence and loss of nodes. This frame-work comprises components for independent and interactive prediction and for predicting new nodes. Our experimental study using real-world data confirms that our interdependent prediction framework achieves higher accuracy than methods based on independent prediction.</abstract>
<identifier type="citekey">yamasaki-etal-2023-holistic</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.765</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.765</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13676</start>
<end>13694</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Holistic Prediction on a Time-Evolving Attributed Graph
%A Yamasaki, Shohei
%A Sasaki, Yuya
%A Karras, Panagiotis
%A Onizuka, Makoto
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F yamasaki-etal-2023-holistic
%X Graph-based prediction is essential in NLP tasks such as temporal knowledge graph completion. A cardinal question in this field is, how to predict the future links, nodes, and attributes of a time-evolving attributed graph? Unfortunately, existing techniques assume that each link, node, and attribute prediction is independent, and fall short of predicting the appearance of new nodes that were not observed in the past. In this paper, we address two interrelated questions; (1) can we exploit task interdependence to improve prediction accuracy? and (2) can we predict new nodes with their attributes? We propose a unified framework that predicts node attributes and topology changes such as the appearance and disappearance of links and the emergence and loss of nodes. This frame-work comprises components for independent and interactive prediction and for predicting new nodes. Our experimental study using real-world data confirms that our interdependent prediction framework achieves higher accuracy than methods based on independent prediction.
%R 10.18653/v1/2023.acl-long.765
%U https://aclanthology.org/2023.acl-long.765
%U https://doi.org/10.18653/v1/2023.acl-long.765
%P 13676-13694
Markdown (Informal)
[Holistic Prediction on a Time-Evolving Attributed Graph](https://aclanthology.org/2023.acl-long.765) (Yamasaki et al., ACL 2023)
ACL
- Shohei Yamasaki, Yuya Sasaki, Panagiotis Karras, and Makoto Onizuka. 2023. Holistic Prediction on a Time-Evolving Attributed Graph. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13676–13694, Toronto, Canada. Association for Computational Linguistics.