MiNT: Multi-Network Transfer Benchmark for Temporal Graph Learning

Kiarash Shamsi, Tran Gia Bao Ngo, Razieh Shirzadkhani, Shenyang Huang, Farimah Poursafaei, Poupak Azad, Reihaneh Rabbany, Baris Coskunuzer, Guillaume Rabusseau, Cuneyt Gurcan Akcora

Keywords: Temporal graph learning, Transfer learning, Graph neural networks, Temporal multi-network training

TL;DR: We introduce the first benchmark of 84 real-world temporal graphs and MiNT, the first multi-network temporal model pre-trained on this collection, demonstrating strong transferability to unseen token networks.

Abstract: Temporal Graph Learning (TGL) aims to discover patterns in evolving networks or temporal graphs and leverage these patterns to predict future interactions. However, most existing research focuses on learning from a single network in isolation, leaving the challenges of within-domain and cross-domain generalization largely unaddressed. In this study, we introduce a new benchmark of 84 real-world temporal transaction networks and propose **Temporal Multi-network Transfer (MiNT)**, a pre-training framework designed to capture transferable temporal dynamics across diverse networks. We train MiNT models on up to 64 transaction networks and evaluate their generalization ability on 20 held-out, unseen networks. Our results show that MiNT consistently outperforms individually trained models, revealing a strong relation between the number of pre-training networks and transfer performance. These findings highlight scaling trends in temporal graph learning and underscore the importance of network diversity in improving generalization. This work establishes the first large-scale benchmark for studying transferability in TGL and lays the groundwork for developing Temporal Graph Foundation Models. Our code is available at \url{https://github.com/benjaminnNgo/ScalingTGNs}

Dataset URL: https://zenodo.org/records/15364297

Code URL: https://github.com/benjaminnNgo/ScalingTGNs

Primary Area: Datasets & Benchmarks illustrating Different Deep learning Scenarios (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 808