Towards Neural Scaling Laws for Foundation Models on Temporal Graphs

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

Keywords: Temporal graph learning, foundation model, graph neural networks, neural scaling law

TL;DR: We introduce a collection of 84 real world temporal graphs and demonstrate that a TGNN pre-trained on a collection of temporal graphs can transfer positively to downstream unseen token networks.

Abstract:

The field of temporal graph learning aims to learn from evolving network data to forecast future interactions. Given a collection of observed temporal graphs, is it possible to predict the evolution of an unseen network from the same domain?
To answer this question, we first present the Temporal Graph Scaling (TGS) dataset, a large collection of temporal graphs consisting of eighty-four ERC20 token transaction networks collected from 2017 to 2023. Next, we evaluate the transferability of Temporal Graph Neural Networks (TGNNs) for the temporal graph property prediction task by pre-training on a collection of up to sixty-four token transaction networks and then evaluating the downstream performance on twenty unseen token networks. We find that the neural scaling law observed in NLP and Computer Vision also applies in temporal graph learning, where pre-training on a greater number of networks leads to improved downstream performance. To the best of our knowledge, this is the first empirical demonstration of the transferability of temporal graph learning. On downstream token networks, the largest pre-trained model outperforms single model TGNNs on thirteen unseen test networks. Therefore, we believe that this is a promising first step towards building foundation models for temporal graphs. We provide the implementation of TGS at https://anonymous.4open.science/r/ScalingTGNs.

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8220