Iterative Adversarial Inference with Re-Inference Chain for Deep Graphical Models

Zhihao LIU  Hui YIN  Hua HUANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.8   pp.1586-1589
Publication Date: 2019/08/01
Publicized: 2019/05/07
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8256
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
deep graphical model,  generative adversarial nets,  latent variable,  inference,  generation,  

Full Text: PDF>>
Buy this Article

Deep Graphical Model (DGM) based on Generative Adversarial Nets (GANs) has shown promise in image generation and latent variable inference. One of the typical models is the Iterative Adversarial Inference model (GibbsNet), which learns the joint distribution between the data and its latent variable. We present RGNet (Re-inference GibbsNet) which introduces a re-inference chain in GibbsNet to improve the quality of generated samples and inferred latent variables. RGNet consists of the generative, inference, and discriminative networks. An adversarial game is cast between the generative and inference networks and the discriminative network. The discriminative network is trained to distinguish between (i) the joint inference-latent/data-space pairs and re-inference-latent/data-space pairs and (ii) the joint sampled-latent/generated-data-space pairs. We show empirically that RGNet surpasses GibbsNet in the quality of inferred latent variables and achieves comparable performance on image generation and inpainting tasks.