wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
arXiv:2109.11519 · doi:10.1007/978-3-030-93409-5_31
Abstract
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.
References in corpus (10)
- The structure and function of complex networks
- A Comprehensive Survey on Graph Neural Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Analysis of weighted networks
- Fast Graph Representation Learning with PyTorch Geometric
- Simple and Deep Graph Convolutional Networks
- Correlation Networks Among Currencies
- Machine learning dismantling and early-warning signals of disintegration in complex systems
- Signed Graph Convolutional Network
- Learning Multi-Stage Sparsification for Maximum Clique Enumeration