Interactive bi-space embedding based temporal graph learning framework

Zhou, Yuchen

doi:10.1016/j.patcog.2026.114461

Interactive bi-space embedding based temporal graph learning framework

2026-07-01

0

PRE

AI

DOI：10.1016/j.patcog.2026.114461

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Temporal graph representation learning

Hyperbolic temporal graph neural network

Temporal graph mining

Bi-space embedding

Interactive bi-space embedding based temporal graph learning framework

Abstract

Journal

Organization

Cited Papers