wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
This addresses a gap in GNNs for handling ubiquitous signed and weighted graphs, but it is incremental as it extends existing GAT layers.
The paper tackles the problem of learning representations on graphs with signed and weighted links, such as in trust and correlation networks, by proposing wsGAT, an extension of Graph Attention Networks, and shows that it outperforms GCNII and SGCN in link prediction tasks without performance loss when predicting signed weights.
Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to address the lack of GNNs that can handle graphs with signed and weighted links, which are ubiquitous, for instance, in trust and correlation networks. We first evaluate the performance of our proposal by comparing against GCNII in the weighed link prediction task, and against SGCN in the link sign prediction task. After that, we combine the two tasks and show their performance on predicting the signed weight of links, and their existence. Our results on real-world networks show that models with wsGAT layers outperform the ones with GCNII and SGCN layers, and that there is no loss in performance when signed weights are predicted.