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 2002.08274cs.LGstat.ML
收藏

图神经网络回归中的残差相关

Residual Correlation in Graph Neural Network Regression

Cornell University(康奈尔大学)

Junteng Jia, Austin R. Benson

摘要:

图神经网络将每个顶点邻域中的特征转换为该顶点的矢量表示。之后,每个顶点的表示被独立地用于预测其标签。这个标准管道隐含地假设顶点标签在给定其邻域特征的情况下是条件独立的。然而,这是一个强有力的假设,我们证明了在许多现实世界的图数据集上这是不正确的。专注于回归任务,我们发现这种条件独立性假设严重限制了预测能力。这并不令人惊讶,因为传统的基于图的半监督学习方法(如标签传播)通过显式地对预测结果中的相关性进行建模,以相反的方式工作。在这里,我们用一个可解释的和有效的框架来解决这个问题,这个框架可以简单地通过利用回归残差中的相关结构来改进任何图神经网络架构。特别是,我们模型的联合分布的残差顶点与参数化的多元高斯,并估计参数最大化的边际似然观察到的标签。我们的框架实现了比竞争基线更高的准确性,并且学习的参数可以被解释为连接顶点之间的相关性强度。此外,我们开发了线性时间算法,用于低方差,无偏模型参数估计,使我们能够扩展到大型网络。我们还提供了一个基本版本的方法,使更强的假设相关性结构,但无痛实施,往往导致很大的实际性能与最小的开销。

英文摘要:

A graph neural network transforms features in each vertex's neighborhood into a vector representation of the vertex. Afterward, each vertex's representation is used independently for predicting its label. This standard pipeline implicitly assumes that vertex labels are conditionally independent given their neighborhood features. However, this is a strong assumption, and we show that it is far from true on many real-world graph datasets. Focusing on regression tasks, we find that this conditional independence assumption severely limits predictive power. This should not be that surprising, given that traditional graph-based semi-supervised learning methods such as label propagation work in the opposite fashion by explicitly modeling the correlation in predicted outcomes. Here, we address this problem with an interpretable and efficient framework that can improve any graph neural network architecture simply by exploiting correlation structure in the regression residuals. In particular, we model the joint distribution of residuals on vertices with a parameterized multivariate Gaussian, and estimate the parameters by maximizing the marginal likelihood of the observed labels. Our framework achieves substantially higher accuracy than competing baselines, and the learned parameters can be interpreted as the strength of correlation among connected vertices. Furthermore, we develop linear time algorithms for low-variance, unbiased model parameter estimates, allowing us to scale to large networks. We also provide a basic version of our method that makes stronger assumptions on correlation structure but is painless to implement, often leading to great practical performance with minimal overhead.

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。

↑