2022/02/25 by Γεώργιος Κόλλιας, Kollias, Georgios, Vasileios Kalantzis +7 · 1 citation
Computer Science · Physics and Astronomy · Biochemistry, Genetics and Molecular Biology · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #Bioinformatics and Genomic Networks
paper · pdf · doi:10.48550/arxiv.2202.12449
We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes of directed graphs, and uses parameterized graph convolutional network (GCN) layers for its encoder and an asymmetric inner product decoder. Parameters in the encoder control the weighting of representations exchanged between neighboring nodes. We demonstrate the ability of the proposed model to learn meaningful latent embeddings and achieve superior performance on the directed link prediction task on several popular network datasets.