Rethinking Link Prediction for Directed Graphs

TL;DR

This paper critically evaluates current directed link prediction methods, introduces a comprehensive benchmark, and proposes a novel auto-encoder model that achieves state-of-the-art results, advancing understanding and performance in the field.

Contribution

It offers a unified framework for assessing method expressiveness, introduces DirLinkBench benchmark, and proposes SDGAE, a new model with improved performance and theoretical insights.

Findings

Current methods underperform on DirLinkBench

DiGAE outperforms baseline methods overall

SDGAE achieves state-of-the-art results on DirLinkBench

Abstract

Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis of their expressiveness and suffer from effective benchmarks for a fair evaluation. In this paper, we propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on directed link prediction performance. To address limitations in current benchmark setups, we introduce DirLinkBench, a robust new benchmark with comprehensive coverage, standardized evaluation, and modular extensibility. The results on DirLinkBench show that current methods struggle to achieve strong performance, while DiGAE outperforms other baselines overall. We further revisit DiGAE theoretically, showing its graph convolution aligns with GCN on an undirected bipartite graph. Inspired by these insights, we propose a novel Spectral Directed Graph Auto-Encoder SDGAE that achieves state-of-the-art average performance on DirLinkBench. Finally, we analyze key factors influencing directed link prediction and highlight open challenges in this field.