# MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs

arXiv: https://arxiv.org/abs/2406.10426 · HTML: https://mlsanity.com/paper/2406.10426/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [A Constructive Prediction of the Generalization Error Across Scales](https://mlsanity.com/paper/1909.12673/) (2019)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Exploring the Limits of Large Scale Pre-training](https://mlsanity.com/paper/2110.02095/) (2021)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024)
- [Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking](https://mlsanity.com/paper/2306.10453/) (2023)
- [Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space](https://mlsanity.com/paper/2107.03767/) (2021)
- [Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities](https://mlsanity.com/paper/2302.01018/) (2023)
- [GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction](https://mlsanity.com/paper/1812.04206/) (2018)
- [Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets](https://mlsanity.com/paper/2310.04292/) (2023)
- [On the Scalability of GNNs for Molecular Graphs](https://mlsanity.com/paper/2404.11568/) (2024)
- [Label Propagation for Zero-shot Classification with Vision-Language Models](https://mlsanity.com/paper/2404.04072/) (2024)
- [textttMiniMol: A Parameter-Efficient Foundation Model for Molecular Learning](https://mlsanity.com/paper/2404.14986/) (2024)
- [BitcoinHeist: Topological Data Analysis for Ransomware Detection on the Bitcoin Blockchain](https://mlsanity.com/paper/1906.07852/) (2019)
- [Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT](https://mlsanity.com/paper/2310.11709/) (2023)
- [Persistence in Complex Systems](https://mlsanity.com/paper/2205.02082/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Survey of Link Prediction in Temporal Networks](https://mlsanity.com/paper/2502.21185/) (2025)
- [A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction](https://mlsanity.com/paper/2605.21916/) (2026)

## Abstract (arXiv)

Temporal Graph Learning (TGL) has become a robust framework for discovering patterns in dynamic networks and predicting future interactions. While existing research has largely concentrated on learning from individual networks, this study explores the potential of learning from multiple temporal networks and its ability to transfer to unobserved networks. To achieve this, we introduce Temporal Multi-network Training MiNT, a novel pre-training approach that learns from multiple temporal networks. With a novel collection of 84 temporal transaction networks, we pre-train TGL models on up to 64 networks and assess their transferability to 20 unseen networks. Remarkably, MiNT achieves state-of-the-art results in zero-shot inference, surpassing models individually trained on each network. Our findings further demonstrate that increasing the number of pre-training networks significantly improves transfer performance. This work lays the groundwork for developing Temporal Graph Foundation Models, highlighting the significant potential of multi-network pre-training in TGL.