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.
@article{arxiv.2111.12128,
title = {On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features},
author = {Emanuele Rossi and Henry Kenlay and Maria I. Gorinova and Benjamin Paul Chamberlain and Xiaowen Dong and Michael Bronstein},
journal= {arXiv preprint arXiv:2111.12128},
year = {2022}
}