DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

TL;DR

DUPLEX introduces a dual GAT framework utilizing Hermitian adjacency decomposition for complex, inductive embeddings of directed graphs, significantly improving performance on sparse nodes and generalizability across tasks.

Contribution

It presents a novel inductive framework combining Hermitian adjacency and dual GAT encoders for better directed graph embeddings, addressing limitations of existing methods.

Findings

Outperforms state-of-the-art models on directed graph tasks.

Enhances embeddings for nodes with sparse connectivity.

Demonstrates strong inductive and task generalization capabilities.

Abstract

Current directed graph embedding methods build upon undirected techniques but often inadequately capture directed edge information, leading to challenges such as: (1) Suboptimal representations for nodes with low in/out-degrees, due to the insufficient neighbor interactions; (2) Limited inductive ability for representing new nodes post-training; (3) Narrow generalizability, as training is overly coupled with specific tasks. In response, we propose DUPLEX, an inductive framework for complex embeddings of directed graphs. It (1) leverages Hermitian adjacency matrix decomposition for comprehensive neighbor integration, (2) employs a dual GAT encoder for directional neighbor modeling, and (3) features two parameter-free decoders to decouple training from particular tasks. DUPLEX outperforms state-of-the-art models, especially for nodes with sparse connectivity, and demonstrates robust inductive capability and adaptability across various tasks. The code is available at https://github.com/alipay/DUPLEX.