Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.22413 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917433212665856 |
|---|---|
| author | Hou, Qinhan Tang, Jing |
| author_facet | Hou, Qinhan Tang, Jing |
| contents | Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a synthetic node-classification benchmark on contextual stochastic block model graphs, where labels are generated by a controllable mixture of local and far-shell signals. We define distance-misaligned training as a mismatch between where label-relevant information lies and where the model allocates communication over graph distance. On this benchmark, we find three points. First, the preferred graph-distance bias changes systematically with task locality. Second, an oracle adaptive controller, given offline access to the task-side distance target, nearly matches the best fixed bias across regimes and strongly improves over a neutral baseline on mixed and local tasks. Third, a task-agnostic zero-gap controller is weaker, indicating that adaptation alone is not enough and that the control target matters. These results suggest that distance-resolved diagnosis is useful for understanding Graph Transformer failures and for designing graph-aware control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22413 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control Hou, Qinhan Tang, Jing Machine Learning Artificial Intelligence Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a synthetic node-classification benchmark on contextual stochastic block model graphs, where labels are generated by a controllable mixture of local and far-shell signals. We define distance-misaligned training as a mismatch between where label-relevant information lies and where the model allocates communication over graph distance. On this benchmark, we find three points. First, the preferred graph-distance bias changes systematically with task locality. Second, an oracle adaptive controller, given offline access to the task-side distance target, nearly matches the best fixed bias across regimes and strongly improves over a neutral baseline on mixed and local tasks. Third, a task-agnostic zero-gap controller is weaker, indicating that adaptation alone is not enough and that the control target matters. These results suggest that distance-resolved diagnosis is useful for understanding Graph Transformer failures and for designing graph-aware control. |
| title | Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.22413 |