Hierarchical Adversarially Learned Inference

2018/02/04 by Mohamed Ishmael Belghazi, Sai Rajeswar, Belghazi, Mohamed Ishmael +9 · 7 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1802.01071

18 pages, 7 figures

arxiv created 2018/02/04 · openalex publication_date 2018/02/04 · arxiv updated 2018/02/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using the adversarial learning paradigm. We demonstrate that the hierarchical structure supports the learning of progressively more abstract representations as well as providing semantically meaningful reconstructions with different levels of fidelity. Furthermore, we show that minimizing the Jensen-Shanon divergence between the generative and inference network is enough to minimize the reconstruction error. The resulting semantically meaningful hierarchical latent structure discovery is exemplified on the CelebA dataset. There, we show that the features learned by our model in an unsupervised way outperform the best handcrafted features. Furthermore, the extracted features remain competitive when compared to several recent deep supervised approaches on an attribute prediction task on CelebA. Finally, we leverage the model's inference network to achieve state-of-the-art performance on a semi-supervised variant of the MNIST digit classification task.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• ImageNet Large Scale Visual Recognition Challenge
• Auxiliary Deep Generative Models
• Adversarial Feature Learning
• Triple Generative Adversarial Nets
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Conditional Image Generation with PixelCNN Decoders
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Stein Latent Optimization for Generative Adversarial Networks
• A Survey of Deep Facial Attribute Analysis
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• Adversarial Code Learning for Image Generation
• Learning Improved Representations by Transferring Incomplete Evidence Across Heterogeneous Tasks
• Learning to infer in recurrent biological networks

Related

• Decomposed Adversarial Learned Inference
• Learning Hierarchical Features from Generative Models
• Adversarial Feature Learning
• An Architecture for Deep, Hierarchical Generative Models
• Generative Adversarial Networks: recent developments