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 2010.13993cs.LGcs.SI
收藏

结合标签传播和简单模型优于图神经网络

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

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

Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin R. Benson

摘要:

图神经网络(GNN)是在图上学习的主要技术。然而,人们对GNN在实践中为什么成功以及它们是否是良好性能所必需的了解相对较少。在这里,我们表明,对于许多标准的直推节点分类基准,我们可以通过将忽略图结构的浅层模型与利用标签结构中相关性的两个简单后处理步骤相结合,来超过或匹配最先进的GNN的性能:(i)“误差相关性”,其扩展训练数据中的残余误差以校正测试数据中的误差;以及(ii)“预测相关性”,平滑测试数据的预测。我们称这个整体过程为正确和平滑(C&S),后处理步骤通过对早期基于图的半监督学习方法的标准标签传播技术进行简单修改来实现。我们的方法在各种基准测试中超过或接近最先进的GNN的性能,只有一小部分参数和数量级更快的运行时间。例如,我们超过了OGB-Products数据集上最知名的GNN性能,参数减少了137倍,训练时间减少了100倍以上。我们的方法的性能突出了如何直接将标签信息纳入学习算法(如在传统技术中所做的)产生简单和实质性的性能增益。我们还可以将我们的技术结合到大型GNN模型中,提供适度的增益。OGB结果的代码位于https://github.com/Chillee/CorrectAndSmooth。

英文摘要:

Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and whether they are necessary for good performance. Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure: (i) an "error correlation" that spreads residual errors in training data to correct errors in test data and (ii) a "prediction correlation" that smooths the predictions on the test data. We call this overall procedure Correct and Smooth (C&S), and the post-processing steps are implemented via simple modifications to standard label propagation techniques from early graph-based semi-supervised learning methods. Our approach exceeds or nearly matches the performance of state-of-the-art GNNs on a wide variety of benchmarks, with just a small fraction of the parameters and orders of magnitude faster runtime. For instance, we exceed the best known GNN performance on the OGB-Products dataset with 137 times fewer parameters and greater than 100 times less training time. The performance of our methods highlights how directly incorporating label information into the learning algorithm (as was done in traditional techniques) yields easy and substantial performance gains. We can also incorporate our techniques into big GNN models, providing modest gains. Our code for the OGB results is at https://github.com/Chillee/CorrectAndSmooth.

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。

↑