Javascript must be enabled to continue!
Interactive Bi-Space Embedding Based Temporal Graph Learning Framework
View through CrossRef
As a fundamental branch of representation learning, temporal graph representation learning has garnered considerable attention from both academic researchers and industry pratitioners. Although existing temporal graph learning methods show good performances, these methods generally embed temporal graph into a single representation space which cannot simultaneously model time-domain features and structure-domain features well. Inevitably, existing works obtain a suboptimal temporal graph representation which further degrades the performance of downstream analysis tasks. To overcome above problem, we theoretically derive a novel Interactive Bi-Space Embedding based Temporal Graph Learning Framework named IBE-TGLF. Specifically, based on feature distribution discrepancy, IBE-TGLF employs two embedding spaces to modeling dynamic graph evolution and temporal graph structure. Through contrastive space alignment, IBE-TGLF can alleviate the semantic gap between different spaces and yield high-performance graph representation. Finally, we conduct extensive experiments on multiple benchmarks to validate the effectiveness and efficiency of IBE-TGLF. Experimental results demonstrate the state-of-the-art performances of IBE-TGLF.
Title: Interactive Bi-Space Embedding Based Temporal Graph Learning Framework
Description:
As a fundamental branch of representation learning, temporal graph representation learning has garnered considerable attention from both academic researchers and industry pratitioners.
Although existing temporal graph learning methods show good performances, these methods generally embed temporal graph into a single representation space which cannot simultaneously model time-domain features and structure-domain features well.
Inevitably, existing works obtain a suboptimal temporal graph representation which further degrades the performance of downstream analysis tasks.
To overcome above problem, we theoretically derive a novel Interactive Bi-Space Embedding based Temporal Graph Learning Framework named IBE-TGLF.
Specifically, based on feature distribution discrepancy, IBE-TGLF employs two embedding spaces to modeling dynamic graph evolution and temporal graph structure.
Through contrastive space alignment, IBE-TGLF can alleviate the semantic gap between different spaces and yield high-performance graph representation.
Finally, we conduct extensive experiments on multiple benchmarks to validate the effectiveness and efficiency of IBE-TGLF.
Experimental results demonstrate the state-of-the-art performances of IBE-TGLF.
Related Results
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
The pandemic Covid-19 currently demands teachers to be able to use technology in teaching and learning process. But in reality there are still many teachers who have not been able ...
Graph convolutional neural networks for 3D data analysis
Graph convolutional neural networks for 3D data analysis
(English) Deep Learning allows the extraction of complex features directly from raw input data, eliminating the need for hand-crafted features from the classical Machine Learning p...
Graph data warehousing
Graph data warehousing
Over the last decade, we have witnessed the emergence of networks in a wide spectrum of application domains, ranging from social and information networks to biological and transpor...
Improvement of Concept Understanding Through the Development of Interactive Multimedia on Integer Operation Material
Improvement of Concept Understanding Through the Development of Interactive Multimedia on Integer Operation Material
Understanding the concept is the ability expected in every learning process. But not all students can master the understanding of the concept well. Researchers are trying to provid...
Temporal Graph Neural Networks for Modeling Student Knowledge Evolution and Predicting Learning Trajectories
Temporal Graph Neural Networks for Modeling Student Knowledge Evolution and Predicting Learning Trajectories
Accurately modeling student knowledge evolution is a central challenge in personalized learning and adaptive educational systems. Traditional sequential or static approaches often ...
Bilangan Terhubung Titik Pelangi pada Graf Garis dan Graf Tengah dari Hasil Operasi Comb Graf Bintang C<sub>3</sub> dan Graf Bintang S<sub>n</sub>
Bilangan Terhubung Titik Pelangi pada Graf Garis dan Graf Tengah dari Hasil Operasi Comb Graf Bintang C<sub>3</sub> dan Graf Bintang S<sub>n</sub>
Penelitian ini bertujuan menentukan bilangan terhubung titik pelangi (rainbow vertex connection number) pada graf garis dan graf tengah yang diperoleh dari hasil operasi comb antar...
A Data-Driven Graph Neural Network Framework for Predicting Topological Indices of Unicyclic and Bicyclic Graphs
A Data-Driven Graph Neural Network Framework for Predicting Topological Indices of Unicyclic and Bicyclic Graphs
Topological indices provide numerical descriptions of graph structure and support graph analysis in cheminformatics, network design, and graph mining. This study presents a reprodu...
Seditious Spaces
Seditious Spaces
The title ‘Seditious Spaces’ is derived from one aspect of Britain’s colonial legacy in Malaysia (formerly Malaya): the Sedition Act 1948. While colonial rule may seem like it was ...

