# Dynamic Graph Convolutional Networks

## TL;DR

This paper introduces two novel neural network architectures that combine LSTM and Graph Convolutional Networks to effectively model dynamic graphs with changing vertices and edges over time, addressing a previously unexplored task.

## Contribution

The paper proposes the first architectures that jointly model structured graph data and temporal dynamics using LSTM and GCNs, filling a gap in current methods.

## Key findings

- Achieved promising results on dynamic graph classification tasks.
- Demonstrated the effectiveness of combining LSTM with GCNs for temporal graph data.
- Showed that the proposed methods outperform baseline approaches.

## Abstract

Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly exploit structured data and temporal information through the use of a neural network model. To the best of our knowledge, this task has not been addressed using these kind of architectures. For this reason, we propose two novel approaches, which combine Long Short-Term Memory networks and Graph Convolutional Networks to learn long short-term dependencies together with graph structure. The quality of our methods is confirmed by the promising results achieved.