Hierarchical Graph Neural Networks
This work addresses a gap in GNN design for researchers and practitioners in network science, offering an incremental improvement by integrating hierarchical approaches from traditional methods.
The paper tackles the divergence between Graph Neural Networks (GNNs) and traditional hierarchical neural network architectures by proposing a Hierarchical Graph Neural Network that incorporates auxiliary network layers to leverage hierarchical organization. The result is improved convergence and stability in tasks like network embedding, classification, and community detection, with demonstrated increased efficiency.
Over the recent years, Graph Neural Networks have become increasingly popular in network analytic and beyond. With that, their architecture noticeable diverges from the classical multi-layered hierarchical organization of the traditional neural networks. At the same time, many conventional approaches in network science efficiently utilize the hierarchical approaches to account for the hierarchical organization of the networks, and recent works emphasize their critical importance. This paper aims to connect the dots between the traditional Neural Network and the Graph Neural Network architectures as well as the network science approaches, harnessing the power of the hierarchical network organization. A Hierarchical Graph Neural Network architecture is proposed, supplementing the original input network layer with the hierarchy of auxiliary network layers and organizing the computational scheme updating the node features through both - horizontal network connections within each layer as well as the vertical connection between the layers. It enables simultaneous learning of the individual node features along with the aggregated network features at variable resolution and uses them to improve the convergence and stability of the individual node feature learning. The proposed Hierarchical Graph Neural network architecture is successfully evaluated on the network embedding and modeling as well as network classification, node labeling, and community tasks and demonstrates increased efficiency in those.