# TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction

arXiv: https://arxiv.org/abs/2506.00453 · HTML: https://mlsanity.com/paper/2506.00453/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 31 May 2025.

## Builds on (most cited first, 30 of 31)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists](https://mlsanity.com/paper/1710.04019/) (2017)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Meta-GNN: On Few-shot Node Classification in Graph Meta-learning](https://mlsanity.com/paper/1905.09718/) (2019)
- [Dynamic Graph Convolutional Networks](https://mlsanity.com/paper/1704.06199/) (2017)
- [Community Interaction and Conflict on the Web](https://mlsanity.com/paper/1803.03697/) (2018)
- [Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting](https://mlsanity.com/paper/2105.04100/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Graph Few-shot Learning via Knowledge Transfer](https://mlsanity.com/paper/1910.03053/) (2019)
- [Link Prediction with Persistent Homology: An Interactive View](https://mlsanity.com/paper/2102.10255/) (2021)
- [Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures](https://mlsanity.com/paper/2002.12815/) (2020)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [Topological Approaches to Deep Learning](https://mlsanity.com/paper/1811.01122/) (2018)
- [Topological Relational Learning on Graphs](https://mlsanity.com/paper/2110.15529/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Meta-Graph: Few Shot Link Prediction via Meta Learning](https://mlsanity.com/paper/1912.09867/) (2019)
- [Going beyond persistent homology using persistent homology](https://mlsanity.com/paper/2311.06152/) (2023)
- [Decoupled Graph Neural Networks for Large Dynamic Graphs](https://mlsanity.com/paper/2305.08273/) (2023)
- [Dissecting Ethereum Blockchain Analytics: What We Learn from Topology and Geometry of Ethereum Graph](https://mlsanity.com/paper/1912.10105/) (2019)
- [Temporal Network Analysis Using Zigzag Persistence](https://mlsanity.com/paper/2205.11338/) (2022)
- [HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities](https://mlsanity.com/paper/2105.07889/) (2021)
- [Graphcode: Learning from multiparameter persistent homology using graph neural networks](https://mlsanity.com/paper/2405.14302/) (2024)
- [Computing Zigzag Persistence on Graphs in Near-Linear Time](https://mlsanity.com/paper/2103.07353/) (2021)
- [Computing Zigzag Vineyard Efficiently Including Expansions and Contractions](https://mlsanity.com/paper/2307.07462/) (2023)
- [The Importance of Forgetting: Limiting Memory Improves Recovery of Topological Characteristics from Neural Data](https://mlsanity.com/paper/1710.11279/) (2017)
- [Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence](https://mlsanity.com/paper/2401.13157/) (2024)
- [Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed Graphs](https://mlsanity.com/paper/2408.09123/) (2024)
- [When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning](https://mlsanity.com/paper/2409.14161/) (2024)
- [Seven open problems in applied combinatorics](https://mlsanity.com/paper/2303.11464/) (2023)

## Built on by (most cited first, 1 of 1)

- [SiST-GNN: Simultaneous Spatial-Temporal Message Passing for Dynamic Graph Representation Learning](https://mlsanity.com/paper/2605.25548/) (2026)

## Abstract (arXiv)

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.