Temporal receptive field in dynamic graph learning: A comprehensive analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karmim, Yannis, Yang, Leshanshui, S'Niehotta, Raphaël Fournier, Chatelain, Clément, Adam, Sébastien, Thome, Nicolas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910534900645888
author Karmim, Yannis
Yang, Leshanshui
S'Niehotta, Raphaël Fournier
Chatelain, Clément
Adam, Sébastien
Thome, Nicolas
author_facet Karmim, Yannis
Yang, Leshanshui
S'Niehotta, Raphaël Fournier
Chatelain, Clément
Adam, Sébastien
Thome, Nicolas
contents Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
format Preprint
id arxiv_https___arxiv_org_abs_2407_12370
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Temporal receptive field in dynamic graph learning: A comprehensive analysis
Karmim, Yannis
Yang, Leshanshui
S'Niehotta, Raphaël Fournier
Chatelain, Clément
Adam, Sébastien
Thome, Nicolas
Machine Learning
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
title Temporal receptive field in dynamic graph learning: A comprehensive analysis
topic Machine Learning
url https://arxiv.org/abs/2407.12370