Apr 25, 2022 · We evaluate our method on several quantitative tasks: author identification, classification, and co-authorship prediction, on two datasets ...

Apr 25, 2022 · We propose a new representation learning model, DGEA (for Dynamic Gaussian Embedding of Authors), that is more suited to solve these tasks by capturing this ...

We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This ...

Mar 6, 2023 · Dynamic Gaussian Embedding of Authors · Fonction : Auteur · PersonId : 3235 · IdHAL : cgravier · ORCID : 0000-0001-8586-6302 · IdRef : 12599396X.

We address this challenge with a novel end-to-end node-embedding model, called Dynamic Embedding for Textual Networks with a Gaussian Process (DetGP).

Oct 5, 2019 · Abstract:Textual network embedding aims to learn low-dimensional representations of text-annotated nodes in a graph.

It improves model capacity by 1) selectively diffusing messages from neighboring nodes and involved attribute categories, and 2) jointly reconstructing node-to- ...

Gaussian embeddings are generally trained with ranking objective and energy functions, such as probability product kernel and KL-divergence. The authors in [ ...

Jan 14, 2022 · It allows to learn evolving authors representations that capture topical or stylistic changes across time. Joint work with.

This work proposes a novel end-to-end node-embedding model, called Dynamic Embedding for Textual Networks with a Gaussian Process (DetGP), which uses the ...