arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09008cs.LGcs.AI
收藏

向量化图机器学习中的长程相互作用:一个大型图数据集和一个度量

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

University of Oxford(牛津大学)

Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan, Michael Bronstein, Xiaowen Dong

AI总结:

本文提出City-Networks数据集,用于研究图机器学习中的长程依赖,通过大规模城市道路网络构建,结合节点偏心率标注,提出基于远距离跳跃邻居雅可比的度量方法,并理论证明其有效性。

摘要:

长程依赖对有效图表示学习至关重要,但现有数据集多聚焦于小图,难以体现长程相互作用。本文引入City-Networks,一个基于真实城市道路网络的大型图数据集,包含超过10^5个节点和更大直径的图,通过局部节点偏心率标注确保分类任务需远距离信息。我们提出基于远距离跳跃邻居雅可比的通用度量方法,提供长程依赖的原理化量化。最后,通过过平滑和影响分数稀释的理论分析,为进一步探索图神经网络中的长程相互作用奠定坚实基础。

英文摘要:

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 $\texttt{City-Networks}$, a novel large-scale transductive learning dataset derived from real-world city road networks. 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 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑