Papers › Effect of Choosing Loss Function when Using T-batching for Representation Learning on...

Effect of Choosing Loss Function when Using T-batching for Representation Learning on Dynamic Networks

13 Aug 2023arXiv:2308.06862archive 2025-07-28

Erfan Loghmani, Mohammadamin Fazli

Representation learning methods have revolutionized machine learning on networks by converting discrete network structures into continuous domains. However, dynamic networks that evolve over time pose new challenges. To address this, dynamic representation learning methods have gained attention, offering benefits like reduced learning time and improved accuracy by utilizing temporal information. T-batching is a valuable technique for training dynamic network models that reduces training time while preserving vital conditions for accurate modeling. However, we have identified a limitation in the training loss function used with t-batching. Through mathematical analysis, we propose two alternative loss functions that overcome these issues, resulting in enhanced training performance. We extensively evaluate the proposed loss functions on synthetic and real-world dynamic networks. The results consistently demonstrate superior performance compared to the original loss function. Notably, in a real-world network characterized by diverse user interaction histories, the proposed loss functions achieved more than 26.9% enhancement in Mean Reciprocal Rank (MRR) and more than 11.8% improvement in Recall@10. These findings underscore the efficacy of the proposed loss functions in dynamic network modeling.

PaperPDFCode

Code

erfanloghmani/effect-of-loss-function-tbatching officialmentioned in papermentioned on GitHubpytorch report
erfanloghmani/myket-android-application-market-dataset officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
M-Lampert/DyGLib mentioned on GitHubpytorch report
qianghuangwhu/benchtemp mentioned on GitHubpytorchMIT report
yule-buaa/dyglib mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Representation LearningLink PredictionRepresentation Learning

Datasets

Introduced by this paper, per the archive.

Myket Android Application Install

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections