Gaussian-Process-Based Dynamic Embedding for Textual Networks

10/05/2019
by   Pengyu Cheng, et al.
0

Textual network embedding aims to learn low-dimensional representations of text-annotated nodes in a graph. Prior works have typically focused on fixed graph structures. However, real-world networks are often dynamic. We address this challenge with a novel end-to-end node-embedding model, called Dynamic Embedding for Textual Networks with a Gaussian Process (DetGP). Because the structure is allowed to be dynamic, our method uses the Gaussian process to take advantage of its non-parametric properties. After training, DetGP can be applied efficiently to dynamic graphs without re-training or backpropagation. To use both local and global graph structures, diffusion is used to model multiple hops between neighbors. The relative importance of global versus local structure for the embeddings is learned automatically. With the non-parametric nature of the Gaussian process, updating the embeddings for a changed graph structure requires only a forward pass through the learned model. Experiments demonstrate the empirical effectiveness of our method compared to baseline approaches, on link prediction and node classification. We further show that DetGP can be straightforwardly and efficiently applied to dynamic textual networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2019

Gaussian Embedding of Large-scale Attributed Graphs

Graph embedding methods transform high-dimensional and complex graph con...
research
11/05/2019

Dynamic Graph Embedding via LSTM History Tracking

Many real world networks are very large and constantly change over time....
research
02/11/2020

Graph Convolutional Gaussian Processes For Link Prediction

Link prediction aims to reveal missing edges in a graph. We address this...
research
05/24/2018

Diffusion Maps for Textual Network Embedding

Textual network embedding leverages rich text information associated wit...
research
08/30/2019

Adversarial Training Methods for Network Embedding

Network Embedding is the task of learning continuous node representation...
research
07/27/2019

DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

Learning topological representation of a network in dynamic environments...
research
05/27/2023

Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction

Accurate citation count prediction of newly published papers could help ...

Please sign up or login with your details

Forgot password? Click here to reset