Skip to yearly menu bar Skip to main content


Poster

DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

Zhaoru Ke · Hang Yu · Jianguo Li · Haipeng Zhang

Hall C 4-9 #505
[ ] [ Paper PDF ]
[ Poster
Thu 25 Jul 2:30 a.m. PDT — 4 a.m. PDT

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 will be available upon publication.

Chat is not available.