Group-Node Attention for Community Evolution Prediction

TL;DR

This paper introduces GNAN, a graph neural network with group-node attention for predicting community evolution in social networks, outperforming standard baselines by leveraging structural and temporal data.

Contribution

The paper presents a novel GNN model with group-node attention for community evolution prediction, supporting variable-sized inputs and learned group representations.

Findings

GNAN outperforms baseline methods in community evolution prediction

Network trends significantly affect model performance

Group-node attention enhances representation of community structures

Abstract

Communities in social networks evolve over time as people enter and leave the network and their activity behaviors shift. The task of predicting structural changes in communities over time is known as community evolution prediction. Existing work in this area has focused on the development of frameworks for defining events while using traditional classification methods to perform the actual prediction. We present a novel graph neural network for predicting community evolution events from structural and temporal information. The model (GNAN) includes a group-node attention component which enables support for variable-sized inputs and learned representation of groups based on member and neighbor node features. A comparative evaluation with standard baseline methods is performed and we demonstrate that our model outperforms the baselines. Additionally, we show the effects of network trends on model performance.