Deep Graph Neural Point Process For Learning Temporal Interactive Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Su, Qi, Xiaohua, Lin, Xixun, Shang, Yanmin, Xu, Xiaolin, Li, Yangxi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916906022207488
author Chen, Su
Qi, Xiaohua
Lin, Xixun
Shang, Yanmin
Xu, Xiaolin
Li, Yangxi
author_facet Chen, Su
Qi, Xiaohua
Lin, Xixun
Shang, Yanmin
Xu, Xiaolin
Li, Yangxi
contents Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point Process(DGNPP) model for TIN is proposed. DGNPP consists of two key modules: the Node Aggregation Layer and the Self Attentive Layer. The Node Aggregation Layer captures topological structures to generate static representation for users and items, while the Self Attentive Layer dynamically updates embeddings over time. By incorporating both dynamic and static embeddings into the event intensity function and optimizing the model via maximum likelihood estimation, DGNPP predicts events and occurrence time effectively. Experimental evaluations on three public datasets demonstrate that DGNPP achieves superior performance in event prediction and time prediction tasks with high efficiency, significantly outperforming baseline models and effectively mitigating the limitations of prior approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Graph Neural Point Process For Learning Temporal Interactive Networks
Chen, Su
Qi, Xiaohua
Lin, Xixun
Shang, Yanmin
Xu, Xiaolin
Li, Yangxi
Machine Learning
Artificial Intelligence
Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point Process(DGNPP) model for TIN is proposed. DGNPP consists of two key modules: the Node Aggregation Layer and the Self Attentive Layer. The Node Aggregation Layer captures topological structures to generate static representation for users and items, while the Self Attentive Layer dynamically updates embeddings over time. By incorporating both dynamic and static embeddings into the event intensity function and optimizing the model via maximum likelihood estimation, DGNPP predicts events and occurrence time effectively. Experimental evaluations on three public datasets demonstrate that DGNPP achieves superior performance in event prediction and time prediction tasks with high efficiency, significantly outperforming baseline models and effectively mitigating the limitations of prior approaches.
title Deep Graph Neural Point Process For Learning Temporal Interactive Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.13219