On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
arXiv:2111.12128
Abstract
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.
References in corpus (20)
- Auto-Encoding Variational Bayes
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Modeling polypharmacy side effects with graph convolutional networks
- Fast Graph Representation Learning with PyTorch Geometric
- Simplifying Graph Convolutional Networks
- Graph Convolutional Matrix Completion
- Representation Learning on Graphs with Jumping Knowledge Networks
- Pitfalls of Graph Neural Network Evaluation
- GAIN: Missing Data Imputation using Generative Adversarial Nets
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- Learning to Simulate Complex Physics with Graph Networks
- Matrix Completion on Graphs
- Learning on Attribute-Missing Graphs
- Graph Convolutional Networks for Graphs Containing Missing Features
- Incomplete Graph Representation and Learning via Partial Graph Neural Networks
- On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
- Random Features Strengthen Graph Neural Networks
- GRAND: Graph Neural Diffusion