Understanding the Design Principles of Link Prediction in Directed Settings

TL;DR

This paper investigates the principles of link prediction in directed graphs, proposing adaptations of undirected heuristics, and introduces a new framework that outperforms existing methods on multiple benchmarks.

Contribution

It offers the first comprehensive evaluation of heuristics for directed link prediction and develops a novel framework that surpasses current state-of-the-art models.

Findings

Directed heuristics can be effectively adapted for link prediction.

The proposed framework outperforms existing GNNs on benchmarks.

Simple heuristic modifications yield competitive results with complex models.

Abstract

Link prediction is a widely studied task in Graph Representation Learning (GRL) for modeling relational data. The early theories in GRL were based on the assumption of a symmetric adjacency matrix, reflecting an undirected setting. As a result, much of the following state-of-the-art research has continued to operate under this symmetry assumption, even though real-world data often involve crucial information conveyed through the direction of relationships. This oversight limits the ability of these models to fully capture the complexity of directed interactions. In this paper, we focus on the challenge of directed link prediction by evaluating key heuristics that have been successful in undirected settings. We propose simple but effective adaptations of these heuristics to the directed link prediction task and demonstrate that these modifications produce competitive performance compared to the leading Graph Neural Networks (GNNs) originally designed for undirected graphs. Through an extensive set of experiments, we derive insights that inform the development of a novel framework for directed link prediction, which not only surpasses baseline methods but also outperforms state-of-the-art GNNs on multiple benchmarks.