Papers › Segmented Graph-Bert for Graph Instance Modeling
Segmented Graph-Bert for Graph Instance Modeling
Jiawei Zhang
In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In this paper, we will examine the effectiveness of GRAPH-BERT on graph instance representation learning, which was designed for node representation learning tasks originally. To adapt GRAPH-BERT to the new problem settings, we re-design it with a segmented architecture instead, which is also named as SEG-BERT (Segmented GRAPH-BERT) for reference simplicity in this paper. SEG-BERT involves no node-order-variant inputs or functional components anymore, and it can handle the graph node orderless property naturally. What's more, SEG-BERT has a segmented architecture and introduces three different strategies to unify the graph instance sizes, i.e., full-input, padding/pruning and segment shifting, respectively. SEG-BERT is pre-trainable in an unsupervised manner, which can be further transferred to new tasks directly or with necessary fine-tuning. We have tested the effectiveness of SEG-BERT with experiments on seven graph instance benchmark datasets, and SEG-BERT can out-perform the comparison methods on six out of them with significant performance advantages.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Graph Classification | COLLAB | SEG-BERT | Accuracy | 78.42% | #19 of 39 | Archive leaderboard | report |
| Graph Classification | IMDb-B | SEG-BERT | Accuracy | 77.2% | #16 of 51 | Archive leaderboard | report |
| Graph Classification | IMDb-M | SEG-BERT | Accuracy | 53.4% | #10 of 36 | Archive leaderboard | report |
| Graph Classification | MUTAG | SEG-BERT | Accuracy | 90.85% | #17 of 74 | Archive leaderboard | report |
| Graph Classification | PROTEINS | SEG-BERT | Accuracy | 77.09% | #37 of 103 | Archive leaderboard | report |
| Graph Classification | PTC | SEG-BERT | Accuracy | 68.86% | #15 of 37 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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