VIGAN: Missing View Imputation with Generative Adversarial Networks

2017/08/22 by Chao Shang, Shang, Chao, Aaron Palmer +11 · 7 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Machine Learning (stat.ML) #cs.CV #stat.ML

paper · pdf · doi:10.48550/arxiv.1708.06724

10 pages, 8 figures, conference

openalex publication_date 2017/08/22 · arxiv created 2017/11/01 · arxiv updated 2017/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In an era when big data are becoming the norm, there is less concern with the quantity but more with the quality and completeness of the data. In many disciplines, data are collected from heterogeneous sources, resulting in multi-view or multi-modal datasets. The missing data problem has been challenging to address in multi-view data analysis. Especially, when certain samples miss an entire view of data, it creates the missing view problem. Classic multiple imputations or matrix completion methods are hardly effective here when no information can be based on in the specific view to impute data for such samples. The commonly-used simple method of removing samples with a missing view can dramatically reduce sample size, thus diminishing the statistical power of a subsequent analysis. In this paper, we propose a novel approach for view imputation via generative adversarial networks (GANs), which we name by VIGAN. This approach first treats each view as a separate domain and identifies domain-to-domain mappings via a GAN using randomly-sampled data from each view, and then employs a multi-modal denoising autoencoder (DAE) to reconstruct the missing view from the GAN outputs based on paired data across the views. Then, by optimizing the GAN and DAE jointly, our model enables the knowledge integration for domain mappings and view correspondences to effectively recover the missing view. Empirical results on benchmark datasets validate the VIGAN approach by comparing against the state of the art. The evaluation of VIGAN in a genetic study of substance use disorders further proves the effectiveness and usability of this approach in life science.

Citations

• Adam: A Method for Stochastic Optimization
• Diagnostic reliability of the Semi-structured Assessment for Drug Dependence and Alcoholism (SSADDA)
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Triple Generative Adversarial Nets
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Cited by

• Towards Robust Optical-SAR Object Detection under Missing Modalities: A Dynamic Quality-Aware Fusion Framework
• Simple Yet Effective Selective Imputation for Incomplete Multi-view Clustering
• An Interdisciplinary and Cross-Task Review on Missing Data Imputation
• Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets
• Missing-Modality-Aware Graph Neural Network for Cancer Classification
• Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion
• Imputation-free Learning of Tabular Data with Missing Values using Incremental Feature Partitions in Transformer

Related

• Effective and Efficient Multi-View Imputation With Optimal Transport
• GAIN: Missing Data Imputation using Generative Adversarial Nets
• IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks
• Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
• Impugan: Learning Conditional Generative Models for Robust Data Imputation