D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning

TL;DR

D-HYPR introduces a novel hyperbolic neural network framework that effectively models neighborhoods and preserves asymmetry in directed graphs, outperforming existing methods across multiple tasks and datasets.

Contribution

The paper proposes D-HYPR, a new digraph representation learning method that generalizes to complex digraphs and multiple tasks, addressing limitations of prior models.

Findings

D-HYPR significantly outperforms 21 prior techniques.

Effective on diverse real-world digraph datasets.

Applicable to node classification, link prediction, and property prediction.

Abstract

Digraph Representation Learning (DRL) aims to learn representations for directed homogeneous graphs (digraphs). Prior work in DRL is largely constrained (e.g., limited to directed acyclic graphs), or has poor generalizability across tasks (e.g., evaluated solely on one task). Most Graph Neural Networks (GNNs) exhibit poor performance on digraphs due to the neglect of modeling neighborhoods and preserving asymmetry. In this paper, we address these notable challenges by leveraging hyperbolic collaborative learning from multi-ordered and partitioned neighborhoods, and regularizers inspired by socio-psychological factors. Our resulting formalism, Digraph Hyperbolic Networks (D-HYPR) - albeit conceptually simple - generalizes to digraphs where cycles and non-transitive relations are common, and is applicable to multiple downstream tasks including node classification, link presence prediction, and link property prediction. In order to assess the effectiveness of D-HYPR, extensive evaluations were performed across 8 real-world digraph datasets involving 21 prior techniques. D-HYPR statistically significantly outperforms the current state of the art. We release our code at https://github.com/hongluzhou/dhypr