Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ko, Yunyong, Lee, Da Eun, Yu, Song Kyung, Kim, Sang-Wook
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914002120998912
author Ko, Yunyong
Lee, Da Eun
Yu, Song Kyung
Kim, Sang-Wook
author_facet Ko, Yunyong
Lee, Da Eun
Yu, Song Kyung
Kim, Sang-Wook
contents Real-world networks have high-order relationships among objects and they evolve over time. To capture such dynamics, many works have been studied in a range of fields. Via an in-depth preliminary analysis, we observe two important characteristics of high-order dynamics in real-world networks: high-order relations tend to (O1) have a structural and temporal influence on other relations in a short term and (O2) periodically re-appear in a long term. In this paper, we propose LINCOLN, a method for Learning hIgh-order dyNamiCs Of reaL-world Networks, that employs (1) bi-interactional hyperedge encoding for short-term patterns, (2) periodic time injection and (3) intermediate node representation for long-term patterns. Via extensive experiments, we show that LINCOLN outperforms nine state-of-the-art methods in the dynamic hyperedge prediction task.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17236
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks
Ko, Yunyong
Lee, Da Eun
Yu, Song Kyung
Kim, Sang-Wook
Social and Information Networks
Machine Learning
Real-world networks have high-order relationships among objects and they evolve over time. To capture such dynamics, many works have been studied in a range of fields. Via an in-depth preliminary analysis, we observe two important characteristics of high-order dynamics in real-world networks: high-order relations tend to (O1) have a structural and temporal influence on other relations in a short term and (O2) periodically re-appear in a long term. In this paper, we propose LINCOLN, a method for Learning hIgh-order dyNamiCs Of reaL-world Networks, that employs (1) bi-interactional hyperedge encoding for short-term patterns, (2) periodic time injection and (3) intermediate node representation for long-term patterns. Via extensive experiments, we show that LINCOLN outperforms nine state-of-the-art methods in the dynamic hyperedge prediction task.
title Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks
topic Social and Information Networks
Machine Learning
url https://arxiv.org/abs/2508.17236