Directed Graph Auto-Encoders

2022/02/25 by Γεώργιος Κόλλιας, Georgios Kollias, Kollias, Georgios +8 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Bioinformatics and Genomic Networks #Complex Network Analysis Techniques #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2202.12449

AAAI 2022

arxiv created 2022/02/25 · arxiv updated 2022/02/28

Abstract

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.

Cited by

• Directed Link Prediction using GNN with Local and Global Feature Fusion
• Residual Reweighted Conformal Prediction for Graph Neural Networks
• Toward Data-centric Directed Graph Learning: An Entropy-driven Approach

Related

• Variational Graph Auto-Encoders
• Multi-Task Graph Autoencoders
• Rethinking Link Prediction for Directed Graphs
• Simple and Effective Graph Autoencoders with One-Hop Linear Models
• Gravity-Inspired Graph Autoencoders for Directed Link Prediction