TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction

TL;DR

TMetaNet introduces a topological meta-learning framework that leverages high-order dynamic graph features for improved link prediction, demonstrating superior performance and noise resilience on real-world datasets.

Contribution

It develops a novel topological feature representation method and integrates it into a meta-learning model for dynamic graphs, addressing limitations of fixed parameter updates.

Findings

Achieves state-of-the-art dynamic link prediction accuracy.

Demonstrates robustness to graph noise.

Effectively captures high-order topological features.

Abstract

Dynamic graphs evolve continuously, presenting challenges for traditional graph learning due to their changing structures and temporal dependencies. Recent advancements have shown potential in addressing these challenges by developing suitable meta-learning-based dynamic graph neural network models. However, most meta-learning approaches for dynamic graphs rely on fixed weight update parameters, neglecting the essential intrinsic complex high-order topological information of dynamically evolving graphs. We have designed Dowker Zigzag Persistence (DZP), an efficient and stable dynamic graph persistent homology representation method based on Dowker complex and zigzag persistence, to capture the high-order features of dynamic graphs. Armed with the DZP ideas, we propose TMetaNet, a new meta-learning parameter update model based on dynamic topological features. By utilizing the distances between high-order topological features, TMetaNet enables more effective adaptation across snapshots. Experiments on real-world datasets demonstrate TMetaNet's state-of-the-art performance and resilience to graph noise, illustrating its high potential for meta-learning and dynamic graph analysis. Our code is available at https://github.com/Lihaogx/TMetaNet.