Conference item
Towards quantifying long-range interactions in graph machine learning: a large graph dataset and a measurement
- Abstract:
-
Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited insight into long-range interactions. Current evaluations primarily compare models employing global attention (e.g., graph transformers) with those using local neighborhood aggregation (e.g., message-passing neural networks) without a direct measurement of long-range dependency. In this work, we introduce City-Networks, a novel large-scale transductive learning dataset derived from real-world city road networks. This dataset features graphs with over 105 nodes and significantly larger diameters than those in existing benchmarks, naturally embodying long-range information. We annotate the graphs based on local node eccentricities, ensuring that the classification task inherently requires information from distant nodes. Furthermore, we propose a generic measurement based on the Jacobians of neighbors from distant hops, offering a principled quantification of long-range dependencies. Finally, we provide theoretical justifications for both our dataset design and the proposed measurement—particularly by focusing on over-smoothing and influence score dilution—which establishes a robust foundation for further exploration of long-range interactions in graph neural networks.
- Publication status:
- Accepted
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 7.7MB, Terms of use)
-
- Publication website:
- https://openreview.net/forum?id=fylMiUmg39
Authors
- Funder identifier:
- https://ror.org/03n0ht308
- Grant:
- 2884089
- Publisher:
- OpenReview
- Host title:
- Proceedings of the 14th International Conference on Learning Representations (ICLR 2026)
- Article number:
- 6143
- Acceptance date:
- 2026-01-26
- Event title:
- 14th International Conference on Learning Representations (ICLR 2026)
- Event location:
- Rio de Janeiro, Brazil
- Event website:
- https://iclr.cc/Conferences/2026
- Event start date:
- 2026-04-23
- Event end date:
- 2026-04-27
- Language:
-
English
- Pubs id:
-
2426912
- Local pid:
-
pubs:2426912
- Deposit date:
-
2026-05-30
- ARK identifier:
Terms of use
- Copyright holder:
- Liang et al.
- Copyright date:
- 2026
- Rights statement:
- © The Authors 2026.
- Notes:
- The author accepted manuscript (AAM) of this paper has been made available under the University of Oxford's Open Access Publications Policy, and a CC BY public copyright licence has been applied.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record