Graph Convolutional Networks for Graphs Containing Missing Features

Abstract

Graph Convolutional Network (GCN) has experienced great success in graph analysis tasks. It works by smoothing the node features across the graph. The current GCN models overwhelmingly assume that the node feature information is complete. However, real-world graph data are often incomplete and containing missing features. Traditionally, people have to estimate and fill in the unknown features based on imputation techniques and then apply GCN. However, the process of feature filling and graph learning are separated, resulting in degraded and unstable performance. This problem becomes more serious when a large number of features are missing. We propose an approach that adapts GCN to graphs containing missing features. In contrast to traditional strategy, our approach integrates the processing of missing features and graph learning within the same neural network architecture. Our idea is to represent the missing data by Gaussian Mixture Model (GMM) and calculate the expected activation of neurons in the first hidden layer of GCN, while keeping the other layers of the network unchanged. This enables us to learn the GMM parameters and network weight parameters in an end-to-end manner. Notably, our approach does not increase the computational complexity of GCN and it is consistent with GCN when the features are complete. We demonstrate through extensive experiments that our approach significantly outperforms the imputation-based methods in node classification and link prediction tasks. We show that the performance of our approach for the case with a low level of missing features is even superior to GCN for the case with complete features.

References in corpus (39)

• Auto-Encoding Variational Bayes
• DeepWalk: Online Learning of Social Representations
• MissForest - nonparametric missing value imputation for mixed-type data
• LINE: Large-scale Information Network Embedding
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Graph Neural Networks: A Review of Methods and Applications
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• How to project a bipartite network?
• Adversarial Attacks on Neural Networks for Graph Data
• Variational Graph Auto-Encoders
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• GAIN: Missing Data Imputation using Generative Adversarial Nets
• Learning Graph Embedding with Adversarial Training Methods
• Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection
• Link Prediction Based on Graph Neural Networks
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• Hyperbolic Graph Convolutional Neural Networks
• Missing Data Imputation with Adversarially-trained Graph Convolutional Networks
• Deep Learning on Graphs: A Survey
• Adversarial Attack on Graph Structured Data
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Certifiable Robustness and Robust Training for Graph Convolutional Networks
• RGCNN: Regularized Graph CNN for Point Cloud Segmentation
• Hyperbolic Graph Neural Networks
• Processing of missing data by neural networks
• GraphIE: A Graph-Based Framework for Information Extraction
• Local Spectral Graph Convolution for Point Set Feature Learning
• MisGAN: Learning from Incomplete Data with Generative Adversarial Networks
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• Graph Learning Approaches to Recommender Systems: A Review
• Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach
• Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
• Feature-Attention Graph Convolutional Networks for Noise Resilient Learning

Cited by in corpus (10)

• FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
• Learning Strong Graph Neural Networks with Weak Information
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Deconvolutional Networks on Graph Data
• Scaling Methods To Estimate Macroscopic Fundamental Diagrams in Urban Networks with Sparse Sensor Coverage
• Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective
• Cyberswarm: a novel swarm intelligence algorithm inspired by cyber community dynamics