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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shamsi, Kiarash, Ngo, Tran Gia Bao, Shirzadkhani, Razieh, Huang, Shenyang, Poursafaei, Farimah, Azad, Poupak, Rabbany, Reihaneh, Coskunuzer, Baris, Rabusseau, Guillaume, Akcora, Cuneyt Gurcan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929716428013568
author Shamsi, Kiarash
Ngo, Tran Gia Bao
Shirzadkhani, Razieh
Huang, Shenyang
Poursafaei, Farimah
Azad, Poupak
Rabbany, Reihaneh
Coskunuzer, Baris
Rabusseau, Guillaume
Akcora, Cuneyt Gurcan
author_facet Shamsi, Kiarash
Ngo, Tran Gia Bao
Shirzadkhani, Razieh
Huang, Shenyang
Poursafaei, Farimah
Azad, Poupak
Rabbany, Reihaneh
Coskunuzer, Baris
Rabusseau, Guillaume
Akcora, Cuneyt Gurcan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10426
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
Shamsi, Kiarash
Ngo, Tran Gia Bao
Shirzadkhani, Razieh
Huang, Shenyang
Poursafaei, Farimah
Azad, Poupak
Rabbany, Reihaneh
Coskunuzer, Baris
Rabusseau, Guillaume
Akcora, Cuneyt Gurcan
Machine Learning
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.
title MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
topic Machine Learning
url https://arxiv.org/abs/2406.10426