Temporal Graph Networks for Deep Learning on Dynamic Graphs

by   Emanuele Rossi, et al.

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events. Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient. We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework. We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs.


page 1

page 2

page 3

page 4


FDGNN: Fully Dynamic Graph Neural Network

Dynamic Graph Neural Networks recently became more and more important as...

Analysis of different temporal graph neural network configurations on dynamic graphs

In recent years, there has been an increasing interest in the use of gra...

Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions

Learning on evolving(dynamic) graphs has caught the attention of researc...

Representing Social Networks as Dynamic Heterogeneous Graphs

Graph representations for real-world social networks in the past have mi...

A Method to Predict Semantic Relations on Artificial Intelligence Papers

Predicting the emergence of links in large evolving networks is a diffic...

Deep learning for dynamic graphs: models and benchmarks

Recent progress in research on Deep Graph Networks (DGNs) has led to a m...

Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs

From social networks to protein complexes to disease genomes to visual d...

Code Repositories


Pytorch implementation of "Streaming Graph Neural Network" (not author just trying to reproduce the experiment results)

view repo


A PyTorch annotated replication of the paper: https://arxiv.org/abs/2006.10637

view repo

Please sign up or login with your details

Forgot password? Click here to reset