Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gan, Yanglei, He, Peng, Cai, Yuxiang, Lin, Run, Zhou, Guanyu, Liu, Qiao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917260588744704
author Gan, Yanglei
He, Peng
Cai, Yuxiang
Lin, Run
Zhou, Guanyu
Liu, Qiao
author_facet Gan, Yanglei
He, Peng
Cai, Yuxiang
Lin, Run
Zhou, Guanyu
Liu, Qiao
contents Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08815
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation
Gan, Yanglei
He, Peng
Cai, Yuxiang
Lin, Run
Zhou, Guanyu
Liu, Qiao
Artificial Intelligence
Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.
title Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation
topic Artificial Intelligence
url https://arxiv.org/abs/2602.08815