DeepAI AI Chat
Log In Sign Up

On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features

by   Emanuele Rossi, et al.

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 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.


GIPA: General Information Propagation Algorithm for Graph Learning

Graph neural networks (GNNs) have been popularly used in analyzing graph...

Propagation on Multi-relational Graphs for Node Regression

Recent years have witnessed a rise in real-world data captured with rich...

Node classification for signed networks using diffuse interface methods

Signed networks are a crucial tool when modeling friend and foe relation...

Graph Positional Encoding via Random Feature Propagation

Two main families of node feature augmentation schemes have been explore...

Confidence-Based Feature Imputation for Graphs with Partially Known Features

This paper investigates a missing feature imputation problem for graph l...

DeepNC: Deep Generative Network Completion

Most network data are collected from only partially observable networks ...