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 2106.06707cs.LG
收藏

具有局部图参数的图神经网络

Graph Neural Networks with Local Graph Parameters

PUC Chile(智利天主教大学);IMFD Chile(智利数据基础研究所);University of Antwerp(安特卫普大学)

Pablo Barceló, Floris Geerts, Juan Reutter, Maksimilian Ryschkov

摘要:

最近的各种提议通过在顶点的$k$元组之间传播特征来增加图神经网络的区分能力。已知这些“高阶”GNN的区分能力受$k$维Weisfeiler-Leman(WL)检验的限制,但它们的$\mathcal O(n^k)$存储器要求限制了它们的适用性。其他建议从一开始就将局部高阶图结构信息注入GNN,从而以一次性的、可能是非线性的预处理步骤为代价从GNN继承期望的$\mathcal O(n)$内存需求。我们提出了本地图形参数启用GNNs作为研究后一种方法的框架,并精确地描述了它们的区分能力,在WL测试的变体方面,以及它们可以考虑的图形结构属性方面。局部图参数可以添加到任何GNN架构中,并且计算成本低廉。在表达能力方面,我们的建议位于GNN和高阶对应物的中间。此外,我们提出了几种技术来帮助选择正确的局部图参数。我们的结果将GNNs与有限模型理论和有限变量逻辑中的深层结果联系起来。我们的实验评估表明,添加局部图参数通常对各种GNN,数据集和图学习任务具有积极影响。

英文摘要:

Various recent proposals increase the distinguishing power of Graph Neural Networks GNNs by propagating features between $k$-tuples of vertices. The distinguishing power of these "higher-order'' GNNs is known to be bounded by the $k$-dimensional Weisfeiler-Leman (WL) test, yet their $\mathcal O(n^k)$ memory requirements limit their applicability. Other proposals infuse GNNs with local higher-order graph structural information from the start, hereby inheriting the desirable $\mathcal O(n)$ memory requirement from GNNs at the cost of a one-time, possibly non-linear, preprocessing step. We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account. Local graph parameters can be added to any GNN architecture, and are cheap to compute. In terms of expressive power, our proposal lies in the middle of GNNs and their higher-order counterparts. Further, we propose several techniques to aide in choosing the right local graph parameters. Our results connect GNNs with deep results in finite model theory and finite variable logics. Our experimental evaluation shows that adding local graph parameters often has a positive effect for a variety of GNNs, datasets and graph learning tasks.

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。

↑