Saved in:
Bibliographic Details
Main Authors: Ke, Zhaoru, Yu, Hang, Li, Jianguo, Zhang, Haipeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.05391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929426938200064
author Ke, Zhaoru
Yu, Hang
Li, Jianguo
Zhang, Haipeng
author_facet Ke, Zhaoru
Yu, Hang
Li, Jianguo
Zhang, Haipeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05391
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
Ke, Zhaoru
Yu, Hang
Li, Jianguo
Zhang, Haipeng
Machine Learning
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.
title DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
topic Machine Learning
url https://arxiv.org/abs/2406.05391