A mutually exciting latent space Hawkes process model for continuous-time networks

Z Huang, H Soliman, S Paul… - Uncertainty in artificial …, 2022‏ - proceedings.mlr.press
Networks and temporal point processes serve as fundamental building blocks for modeling
complex dynamic relational data in various domains. We propose the latent space Hawkes …

Intensity profile projection: A framework for continuous-time representation learning for dynamic networks

A Modell, I Gallagher, E Ceccherini… - Advances in …, 2023‏ - proceedings.neurips.cc
We present a new representation learning framework, Intensity Profile Projection, for
continuous-time dynamic network data. Given triples $(i, j, t) $, each representing a time …

Direct embedding of temporal network edges via time-decayed line graphs

S Chanpuriya, RA Rossi, S Kim, T Yu… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Temporal networks model a variety of important phenomena involving timed interactions
between entities. Existing methods for machine learning on temporal networks generally …

The multivariate community hawkes model for dependent relational events in continuous-time networks

H Soliman, L Zhao, Z Huang… - … on Machine Learning, 2022‏ - proceedings.mlr.press
The stochastic block model (SBM) is one of the most widely used generative models for
network data. Many continuous-time dynamic network models are built upon the same …

Continuous-time graph representation with sequential survival process

A Çelikkanat, N Nakis, M Mørup - … of the AAAI Conference on Artificial …, 2024‏ - ojs.aaai.org
Over the past two decades, there has been a tremendous increase in the growth of
representation learning methods for graphs, with numerous applications across various …

Piecewise-velocity model for learning continuous-time dynamic node representations

A Çelikkanat, N Nakis, M Mørup - arxiv preprint arxiv:2212.12345, 2022‏ - arxiv.org
Networks have become indispensable and ubiquitous structures in many fields to model the
interactions among different entities, such as friendship in social networks or protein …

Generalizability and usefulness of artificial intelligence for skin cancer diagnostics: an algorithm validation study

NK Ternov, AN Christensen, PJT Kampen… - JEADV Clinical …, 2022‏ - Wiley Online Library
Background Artificial intelligence can be trained to outperform dermatologists in image‐
based skin cancer diagnostics. However, the networks' sensitivity to biases and overfitting …

The hawkes edge partition model for continuous-time event-based temporal networks

S Yang, H Koeppl - Conference on Uncertainty in Artificial …, 2020‏ - proceedings.mlr.press
We propose a novel probabilistic framework to model continuously generated interaction
events data. Our goal is to infer the\emph {implicit} community structure underlying the …

Time to Cite: Modeling Citation Networks using the Dynamic Impact Single-Event Embedding Model

N Nakis, A Celikkanat, L Boucherie, S Lehmann… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Understanding the structure and dynamics of scientific research, ie, the science of science
(SciSci), has become an important area of research in order to address imminent questions …

Wasserstein generative adversarial networks for modeling marked events

SHS Dizaji, S Pashazadeh, JM Niya - The Journal of Supercomputing, 2023‏ - Springer
Marked temporal events are ubiquitous in several areas, where the events' times and marks
(types) are usually interrelated. Point processes and their non-functional variations using …