# DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

arXiv: https://arxiv.org/abs/2406.05391 · HTML: https://mlsanity.com/paper/2406.05391/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 8 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering](https://mlsanity.com/paper/1708.01471/) (2017)
- [MagNet: A Neural Network for Directed Graphs](https://mlsanity.com/paper/2102.11391/) (2021)
- [Edge Directionality Improves Learning on Heterophilic Graphs](https://mlsanity.com/paper/2305.10498/) (2023)
- [Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations](https://mlsanity.com/paper/1906.05017/) (2019)
- [Gravity-Inspired Graph Autoencoders for Directed Link Prediction](https://mlsanity.com/paper/1905.09570/) (2019)
- [Directed Graph Auto-Encoders](https://mlsanity.com/paper/2202.12449/) (2022)
- [Node Representation Learning for Directed Graphs](https://mlsanity.com/paper/1810.09176/) (2018)
- [Adversarial Directed Graph Embedding](https://mlsanity.com/paper/2008.03667/) (2020)
- [A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs](https://mlsanity.com/paper/2210.10993/) (2022)
- [D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning](https://mlsanity.com/paper/2112.11734/) (2021)
- [Model of complex networks based on citation dynamics](https://mlsanity.com/paper/1303.5857/) (2013)
- [Efficient Variational Bayes Learning of Graphical Models with Smooth Structural Changes](https://mlsanity.com/paper/2009.07703/) (2020)
- [Collaborative Bi-Aggregation for Directed Graph Embedding](https://mlsanity.com/paper/2211.02232/) (2022)

## Built on by (most cited first, 7 of 7)

- [Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding](https://mlsanity.com/paper/2503.18010/) (2025)
- [GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding](https://mlsanity.com/paper/2409.04183/) (2024)
- [Commute Graph Neural Networks](https://mlsanity.com/paper/2407.01635/) (2024)
- [Haar-Laplacian for directed graphs](https://mlsanity.com/paper/2411.15527/) (2024)
- [Cross-Attention Graph Neural Networks for Inferring Gene Regulatory Networks with Skewed Degree Distribution](https://mlsanity.com/paper/2412.16220/) (2024)
- [Rethinking Link Prediction for Directed Graphs](https://mlsanity.com/paper/2502.05724/) (2025)
- [GravityGraphSAGE: Link Prediction in Directed Attributed Graphs](https://mlsanity.com/paper/2605.09408/) (2026)

## Abstract (arXiv)

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.