Missing Data Imputation with Adversarially-trained Graph Convolutional Networks

Abstract

Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework for MDI, leveraging recent work in the field of graph neural networks (GNNs). We formulate the MDI task in terms of a graph denoising autoencoder, where each edge of the graph encodes the similarity between two patterns. A GNN encoder learns to build intermediate representations for each example by interleaving classical projection layers and locally combining information between neighbors, while another decoding GNN learns to reconstruct the full imputed data set from this intermediate embedding. In order to speed-up training and improve the performance, we use a combination of multiple losses, including an adversarial loss implemented with the Wasserstein metric and a gradient penalty. We also explore a few extensions to the basic architecture involving the use of residual connections between layers, and of global statistics computed from the data set to improve the accuracy. On a large experimental evaluation, we show that our method robustly outperforms state-of-the-art approaches for MDI, especially for large percentages of missing values.

Published in Neural Networks (2020)

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• MissForest - nonparametric missing value imputation for mixed-type data
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Discrete Signal Processing on Graphs
• GAIN: Missing Data Imputation using Generative Adversarial Nets
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• On the Graph Fourier Transform for Directed Graphs
• Processing of missing data by neural networks

Cited by in corpus (16)

• Graph Convolutional Networks for Graphs Containing Missing Features
• Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns
• Handling Missing Data with Graph Representation Learning
• Simplicial Neural Networks
• Learning Strong Graph Neural Networks with Weak Information
• Data Imputation with Iterative Graph Reconstruction
• Imputation of missing values in multi-view data
• Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data
• SWMLP: Shared Weight Multilayer Perceptron for Car Trajectory Speed Prediction using Road Topographical Features
• DPER: Efficient Parameter Estimation for Randomly Missing Data
• Efficient data augmentation using graph imputation neural networks
• CoRGi: Content-Rich Graph Neural Networks with Attention