arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01404cs.LGcs.SI
收藏

非同调图学习的新基准

New Benchmarks for Learning on Non-Homophilous Graphs

Cornell University(康奈尔大学);Facebook AI(脸书人工智能研究院)

Derek Lim, Xiuyu Li, Felix Hohne, Ser-Nam Lim

摘要:

许多具有图结构的数据都满足同质性原则,这意味着连接的节点在特定属性方面往往是相似的。因此,用于图机器学习任务的无处不在的数据集通常是高度同质的,奖励利用同质性作为归纳偏差的方法。最近的工作已经指出了这个特别的焦点,因为新的非同质数据集已经引入,更适合于低同质性设置的图表示学习模型已经开发出来。然而,这些数据集很小,不适合真正测试新方法在非同性恋环境中的有效性。我们提出了一系列改进的图数据集的节点标签关系,不满足同伦原则。与此同时,我们引入了一个新的措施的存在或不存在的同质性,比现有的措施更适合在不同的制度。我们在我们提出的数据集上对一系列简单的方法和图神经网络进行了基准测试,为进一步的研究提供了新的见解。数据和代码可以在https://github.com/CUAI/Non-Homophily-Benchmarks上找到。

英文摘要:

Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute. As such, ubiquitous datasets for graph machine learning tasks have generally been highly homophilous, rewarding methods that leverage homophily as an inductive bias. Recent work has pointed out this particular focus, as new non-homophilous datasets have been introduced and graph representation learning models better suited for low-homophily settings have been developed. However, these datasets are small and poorly suited to truly testing the effectiveness of new methods in non-homophilous settings. We present a series of improved graph datasets with node label relationships that do not satisfy the homophily principle. Along with this, we introduce a new measure of the presence or absence of homophily that is better suited than existing measures in different regimes. We benchmark a range of simple methods and graph neural networks across our proposed datasets, drawing new insights for further research. Data and codes can be found at https://github.com/CUAI/Non-Homophily-Benchmarks.

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。

↑