Temporal Graph Networks for Deep Learning on Dynamic Graphs

TL;DR

Temporal Graph Networks (TGNs) provide a flexible and efficient framework for deep learning on dynamic graphs, outperforming previous methods and unifying several existing models within a single approach.

Contribution

The paper introduces TGNs, a novel framework that combines memory modules and graph operators for improved learning on evolving graphs, unifying prior models.

Findings

TGNs outperform previous approaches on dynamic graph tasks.

TGNs are more computationally efficient than existing methods.

Several prior models are special cases of TGNs.

Abstract

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.