Litcius/Paper detail

A dynamic graph representation learning based on temporal graph transformer

Ying Zhong, Chenze Huang

2022Alexandria Engineering Journal11 citationsDOIOpen Access PDF

Abstract

The graph neural network has received significant attention in recent years because of its unique role in mining graph-structure data and its ubiquitous application in various fields, such as social networking and recommendation systems. Although most work focuses on learning low-dimensional node representation in static graphs, the dynamic nature of real-world networks makes temporal graphs more practical and significant. In this paper, we propose a dynamic graph representation learning method based on a temporal graph transformer (TGT), which can efficiently preserve high-order information and temporally evolve structural properties by incorporating an update module, an aggregation module, and a propagation module in a single model. The experimental results on three real-world networks demonstrate that the TGT outperforms state-of-the-art baselines for dynamic link prediction and edge classification tasks in terms of both accuracy and efficiency.

Topics & Concepts

Computer scienceGraphTheoretical computer scienceTransformerFeature learningExternal Data RepresentationArtificial intelligenceMachine learningData miningPhysicsQuantum mechanicsVoltageAdvanced Graph Neural NetworksComplex Network Analysis TechniquesHuman Mobility and Location-Based Analysis