Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement
This work addresses the problem of quantifying long-range interactions in graph neural networks for researchers, offering a new dataset and measurement, but it is incremental as it builds on existing evaluation frameworks.
The authors tackled the lack of datasets and measurements for long-range dependencies in graph machine learning by introducing City-Networks, a large-scale dataset with over 100k nodes and larger diameters, and a model-agnostic measurement based on Jacobians, providing a foundation for further exploration.
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 100k 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 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.