Year: 2023
Type: preprint
Abstract: In the last decades, learning over graph data has become one of the most challenging tasks in deep learning. The generally proposed Graph Neural Network (GNN) framework computes a hidden state for every node in the graph by applying nonlinear transformations to its neighborhood. Then updates the node of interest's hidden state. Nevertheless, the node features can contain discriminative information. That can get lost over GNN layers. Here we present a new variant of GNN architecture where we combine node features and GNN activations to learn nodes representations in the graph. We conduct extensive experiments on two graph prediction tasks (node classification and link prediction) and shows that our method can match and outperforms state-of-the-art results
Source: HAL
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4321009896