Edge-Wise Graph-Instructed Neural Networks
This work addresses multi-task regression on graph-structured data, offering an incremental improvement over existing GINN methods.
The authors tackled the limitations of Graph-Instructed Neural Networks (GINNs) for multi-task regression on graph nodes by proposing a novel edge-wise GI (EWGI) layer, resulting in EWGINNs that perform better on Barabasi-Albert graphs and improve training regularization on Erdos-Renyi graphs.
The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural networks. In this work, we discuss the limitations of the Graph-Instructed (GI) layer, and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages of the EWGI layer and we provide numerical evidence that EWGINNs perform better than GINNs over some graph-structured input data, like the ones inferred from the Barabasi-Albert graph, and improve the training regularization on graphs with chaotic connectivity, like the ones inferred from the Erdos-Renyi graph.