Directed Graph Auto-Encoders

TL;DR

This paper presents a novel auto-encoder model for directed graphs that learns interpretable node embeddings using GCN layers, extending the Weisfeiler-Leman algorithm, and demonstrates superior directed link prediction performance.

Contribution

It introduces a new directed graph auto-encoder with interpretable latent representations and an asymmetric decoder, extending existing graph neural network methods.

Findings

Effective directed link prediction on multiple datasets

Learned embeddings are meaningful and interpretable

Model outperforms existing methods in directed graph tasks

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.