From Link Prediction to Forecasting: Information Loss in Batch-based Temporal Graph Learning
Keywords: Graph Neural Network, GNN, Temporal Graph, Dynamic Link Prediction, Dynamic Graph, Temporal Graph Learning, Dynamic Graph Learning, Temporal Graph Neural Network, TGNN, DyGNN, Dynamic Graph Neural Network
TL;DR: Current dynamic link prediction evaluation practices do not properly account for temporal graph data. We propose an alternative evaluation strategy fixing these issues.
Abstract: Dynamic link prediction is an important problem considered by many recent works
proposing various approaches for learning temporal edge patterns. To assess their
efficacy, models are evaluated on publicly available benchmark datasets involving
continuous-time and discrete-time temporal graphs. However, as we show in this
work, the suitability of common batch-oriented evaluation depends on the datasets’
characteristics, which can cause multiple issues: For continuous-time temporal
graphs, fixed-size batches create time windows with different durations, resulting in
an inconsistent dynamic link prediction task. For discrete-time temporal graphs, the
sequence of batches can additionally introduce temporal dependencies that are not
present in the data. In this work, we empirically show that this common evaluation
approach leads to skewed model performance and hinders the fair comparison of
methods. We mitigate this problem by reformulating dynamic link prediction as a
link forecasting task that better accounts for temporal information present in the
data. We provide implementations of our new evaluation method for commonly
used graph learning frameworks.
Supplementary Material: zip
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.
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: 10271
Loading