GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

TL;DR

GCN-SE introduces a learnable attention mechanism for dynamic graphs, improving node classification by effectively weighting temporal snapshots and providing explainability of snapshot importance.

Contribution

The paper proposes GCN-SE, a novel method that applies attention weights to graph snapshots in dynamic graphs, enhancing classification accuracy and interpretability.

Findings

GCN-SE outperforms existing methods on various datasets.

Attention weights correlate with snapshot importance.

The approach offers explainability for dynamic graph models.

Abstract

Graph Convolutional Networks (GCNs) are a popular method from graph representation learning that have proved effective for tasks like node classification tasks. Although typical GCN models focus on classifying nodes within a static graph, several recent variants propose node classification in dynamic graphs whose topologies and node attributes change over time, e.g., social networks with dynamic relationships, or literature citation networks with changing co-authorships. These works, however, do not fully address the challenge of flexibly assigning different importance to snapshots of the graph at different times, which depending on the graph dynamics may have more or less predictive power on the labels. We address this challenge by proposing a new method, GCN-SE, that attaches a set of learnable attention weights to graph snapshots at different times, inspired by Squeeze and Excitation Net (SE-Net). We show that GCN-SE outperforms previously proposed node classification methods on a variety of graph datasets. To verify the effectiveness of the attention weight in determining the importance of different graph snapshots, we adapt perturbation-based methods from the field of explainable machine learning to graphical settings and evaluate the correlation between the attention weights learned by GCN-SE and the importance of different snapshots over time. These experiments demonstrate that GCN-SE can in fact identify different snapshots' predictive power for dynamic node classification.