Group-Node Attention for Community Evolution Prediction
This work addresses community evolution prediction for social network analysis, but it is incremental as it builds on existing frameworks with a new method.
The paper tackled the problem of predicting structural changes in communities over time in social networks, and the result was that their novel graph neural network model (GNAN) with group-node attention outperformed standard baseline methods in comparative evaluation.
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.