PaperScope
LIVE · 2026-09-15 05:40 UTC

Pre-training with Graph Transformers

Jiaming Wang, Thomas Laurent, Xavier Bresson

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.13844 v1
Category
Submitted
2026-09-12

Abstract

This article investigates pre-training strategies for graph transformers in the biochemistry domain. By conducting comprehensive experiments, the study reveals that supervised pre-training using computed properties as labels provides the highest performance gain on downstream tasks. The results also highlight the importance of constraining model capacity to mitigate overfitting in graph transformers.

Comment: 4 pages, 1 table. DLG-KDD 2023 workshop paper

arXiv abs page · PDF · same-day batch