# Gravity-Inspired Graph Autoencoders for Directed Link Prediction

## TL;DR

This paper introduces a gravity-inspired decoder for graph autoencoders to improve directed link prediction, addressing the limitations of existing models that focus on undirected graphs, and demonstrates superior performance on real-world datasets.

## Contribution

The paper proposes a novel gravity-inspired decoder scheme for directed graph autoencoders, enhancing link prediction capabilities in directed graphs.

## Key findings

- Outperforms standard AE and VAE on directed link prediction tasks
- Effective on three real-world directed graphs
- Achieves competitive results compared to baselines

## Abstract

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges. However, these models focus on undirected graphs and therefore ignore the potential direction of the link, which is limiting for numerous real-life applications. In this paper, we extend the graph AE and VAE frameworks to address link prediction in directed graphs. We present a new gravity-inspired decoder scheme that can effectively reconstruct directed graphs from a node embedding. We empirically evaluate our method on three different directed link prediction tasks, for which standard graph AE and VAE perform poorly. We achieve competitive results on three real-world graphs, outperforming several popular baselines.