# EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

## TL;DR

EvolveGCN introduces a novel method for dynamic graph learning by evolving GCN parameters with RNNs, effectively handling changing node sets without relying on node embeddings, and demonstrating superior performance on various tasks.

## Contribution

The paper proposes EvolveGCN, a new approach that evolves GCN parameters over time using RNNs, addressing challenges of dynamic graphs with changing node sets.

## Key findings

- EvolveGCN outperforms related methods in link prediction, edge classification, and node classification.
- The approach effectively models graph evolution without requiring full node history.
- Experimental results show higher accuracy across multiple dynamic graph tasks.

## Abstract

Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly graphs. With the success of these graph neural networks (GNN) in the static setting, we approach further practical scenarios where the graph dynamically evolves. Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics. These methods require the knowledge of a node in the full time span (including both training and testing) and are less applicable to the frequent change of the node set. In some extreme scenarios, the node sets at different time steps may completely differ. To resolve this challenge, we propose EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings. The proposed approach captures the dynamism of the graph sequence through using an RNN to evolve the GCN parameters. Two architectures are considered for the parameter evolution. We evaluate the proposed approach on tasks including link prediction, edge classification, and node classification. The experimental results indicate a generally higher performance of EvolveGCN compared with related approaches. The code is available at \url{https://github.com/IBM/EvolveGCN}.