Poisson–Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

Nan Fang, Yijun Wang, Hao Liao, Sikun Yang
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:1520-1539, 2026.

Abstract

Dynamic knowledge graphs are ubiquitous in today’s {AI} applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependencies becomes crucial for downstream tasks. To address these challenges, this paper proposes PGRE ({Poisson}–Gamma Relational Evolution), a probabilistic model for modeling inter-relational dependencies in dynamic knowledge graphs. PGRE represents multi-relational temporal links via a {Poisson}–{Bernoulli} formulation. It introduces Gamma-distributed latent variables to capture entity–factor associations and cross-relation dependencies mediated by shared latent communities. A Gamma {Markov} process further models the temporal evolution of these latent variables, enabling principled characterization of relational dynamics. Experiments on benchmark datasets show that PGRE achieves competitive performance in link prediction, particularly in sparse settings, while revealing meaningful relational evolution patterns in dynamic knowledge graphs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-fang26a, title = {{Poisson}–Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs}, author = {Fang, Nan and Wang, Yijun and Liao, Hao and Yang, Sikun}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {1520--1539}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/fang26a/fang26a.pdf}, url = {https://proceedings.mlr.press/v337/fang26a.html}, abstract = {Dynamic knowledge graphs are ubiquitous in today’s {AI} applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependencies becomes crucial for downstream tasks. To address these challenges, this paper proposes PGRE ({Poisson}–Gamma Relational Evolution), a probabilistic model for modeling inter-relational dependencies in dynamic knowledge graphs. PGRE represents multi-relational temporal links via a {Poisson}–{Bernoulli} formulation. It introduces Gamma-distributed latent variables to capture entity–factor associations and cross-relation dependencies mediated by shared latent communities. A Gamma {Markov} process further models the temporal evolution of these latent variables, enabling principled characterization of relational dynamics. Experiments on benchmark datasets show that PGRE achieves competitive performance in link prediction, particularly in sparse settings, while revealing meaningful relational evolution patterns in dynamic knowledge graphs.} }
Endnote
%0 Conference Paper %T Poisson–Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs %A Nan Fang %A Yijun Wang %A Hao Liao %A Sikun Yang %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-fang26a %I PMLR %P 1520--1539 %U https://proceedings.mlr.press/v337/fang26a.html %V 337 %X Dynamic knowledge graphs are ubiquitous in today’s {AI} applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependencies becomes crucial for downstream tasks. To address these challenges, this paper proposes PGRE ({Poisson}–Gamma Relational Evolution), a probabilistic model for modeling inter-relational dependencies in dynamic knowledge graphs. PGRE represents multi-relational temporal links via a {Poisson}–{Bernoulli} formulation. It introduces Gamma-distributed latent variables to capture entity–factor associations and cross-relation dependencies mediated by shared latent communities. A Gamma {Markov} process further models the temporal evolution of these latent variables, enabling principled characterization of relational dynamics. Experiments on benchmark datasets show that PGRE achieves competitive performance in link prediction, particularly in sparse settings, while revealing meaningful relational evolution patterns in dynamic knowledge graphs.
APA
Fang, N., Wang, Y., Liao, H. & Yang, S.. (2026). Poisson–Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:1520-1539 Available from https://proceedings.mlr.press/v337/fang26a.html.

Related Material