Temporal receptive field in dynamic graph learning: A comprehensive analysis - Machine Learning and Information Access
Conference Papers Year : 2024

Temporal receptive field in dynamic graph learning: A comprehensive analysis

Abstract

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 .
Fichier principal
Vignette du fichier
MLG_temporal_analysis-6.pdf (1.03 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04647025 , version 1 (16-07-2024)
hal-04647025 , version 2 (18-07-2024)

Identifiers

Cite

Yannis Karmim, Leshanshui Yang, Raphaël Fournier-S'Niehotta, Clément Chatelain, Sébastien Adam, et al.. Temporal receptive field in dynamic graph learning: A comprehensive analysis. MLG Workshop at ECML-PKDD, Sep 2024, Vilnius (Lituanie), France. ⟨hal-04647025v2⟩
145 View
53 Download

Altmetric

Share

More