arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06023cs.LGcs.AI
收藏

用图卷积网络发现比对关系:一个生物医学案例研究

Discovering alignment relations with Graph Convolutional Networks: a biomedical case study

Université de Lorraine(洛林大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);LORIA(洛林计算机科学与应用研究实验室);Orange(Orange公司);Ubisoft(育碧公司);Inria Paris(法国国家信息与自动化研究所巴黎中心);Centre de Recherche des Cordeliers(科德利耶研究中心);Inserm(法国国家健康与医学研究院);Université de Paris(巴黎大学);Sorbonne Université(索邦大学)

Pierre Monnin, Chedy Raïssi, Amedeo Napoli, Adrien Coulet

摘要:

知识图谱可以在数据网络中自由聚合、发布和编辑,因此可能会重叠。因此,一个关键任务在于对齐(或匹配)它们的内容。该任务包括在聚合的知识图谱内识别等价的、更具体的或弱相关的节点。在这篇文章中,我们提出通过(i)使用图卷积网络学习节点嵌入来匹配知识图谱中的节点,使得相似的节点在嵌入空间中具有较低的距离,以及(ii)基于它们的嵌入对节点进行聚类,以便建议同一簇中节点之间的对齐关系。我们用这种方法对药物基因组学领域中对齐知识的现实应用进行了实验,这激发了我们的研究。我们特别研究了领域知识和GCN模型之间的相互作用,重点有以下两个。首先,在学习节点嵌入之前,我们独立或组合地应用与领域知识相关联的推理规则,并测量匹配结果的改进。其次,虽然我们的GCN模型对精确的比对关系是不可知的(例如,等价,弱相似性),我们观察到嵌入空间中的距离与这些不同关系的“强度”是一致的(例如,相等的距离更小),让我们考虑嵌入空间中的聚类和距离作为在我们的案例研究中建议对齐关系的手段。

英文摘要:

Knowledge graphs are freely aggregated, published, and edited in the Web of data, and thus may overlap. Hence, a key task resides in aligning (or matching) their content. This task encompasses the identification, within an aggregated knowledge graph, of nodes that are equivalent, more specific, or weakly related. In this article, we propose to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embeddings, in order to suggest alignment relations between nodes of a same cluster. We conducted experiments with this approach on the real world application of aligning knowledge in the field of pharmacogenomics, which motivated our study. We particularly investigated the interplay between domain knowledge and GCN models with the two following focuses. First, we applied inference rules associated with domain knowledge, independently or combined, before learning node embeddings, and we measured the improvements in matching results. Second, while our GCN model is agnostic to the exact alignment relations (e.g., equivalence, weak similarity), we observed that distances in the embedding space are coherent with the ``strength'' of these different relations (e.g., smaller distances for equivalences), letting us considering clustering and distances in the embedding space as a means to suggest alignment relations in our case study.

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。

↑