论在有缺失节点特征的图上学习时特征传播的不合理的有效性

虽然图谱神经网络（GNNs）最近已经成为关系数据建模的事实标准，但它们对图的节点或边缘特征的可用性提出了一个强有力的假设。然而，在许多现实世界的应用中，特征只有部分可用；例如，在社交网络中，年龄和性别只有一小部分用户可用。我们提出了一种在图机器学习应用中处理缺失特征的一般方法，该方法基于Dirichlet能量的最小化，并导致了图上的扩散型微分方程。这个方程的离散化产生了一个简单、快速和可扩展的算法，我们称之为特征传播。我们的实验表明，所提出的方法在七个常见的节点分类基准上优于以前的方法，并能承受令人惊讶的高比率的特征缺失：平均而言，当99%的特征缺失时，我们只观察到约4%的相对准确性下降。此外，在单个GPU上运行一个有250万个节点和123万条边的图只需要10秒。

原文题目：On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features

原文：While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. The discretization of this equation produces a simple, fast and scalable algorithm which we call Feature Propagation. We experimentally show that the proposed approach outperforms previous methods on seven common node-classification benchmarks and can withstand surprisingly high rates of missing features: on average we observe only around 4% relative accuracy drop when 99% of the features are missing. Moreover, it takes only 10 seconds to run on a graph with ∼2.5M nodes and ∼123M edges on a single GPU.