Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

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 roads. This dataset features graphs with over $10^5$ nodes and significantly larger diameters than those in existing benchmarks, naturally embodying long-range information. We annotate the graphs using an eccentricity-based approach, ensuring that the classification task inherently requires information from distant nodes. Furthermore, we propose a model-agnostic 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.

@article{liang2025_2503.09008,
  title={ Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement },
  author={ Huidong Liang and Haitz Sáez de Ocáriz Borde and Baskaran Sripathmanathan and Michael Bronstein and Xiaowen Dong },
  journal={arXiv preprint arXiv:2503.09008},
  year={ 2025 }
}