Deep Generative Models With Learnable Knowledge Constraints

Authors:
Zhiting Hu Carnegie Mellon University
Zichao Yang
Russ Salakhutdinov Carnegie Mellon University
LIANHUI Qin
Xiaodan Liang Sun Yat-sen University
Haoye Dong Sun Yat-sen University
Eric Xing Petuum Inc. / Carnegie Mellon University

Introduction:

The broad set of deep generative models (DGMs) has achieved remarkable advances.

Abstract:

The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited applicability to the diverse DGMs that can lack a Bayesian formulation or even explicit density evaluation. PR also requires constraints to be fully specified {\it a priori}, which is impractical or suboptimal for complex knowledge with learnable uncertain parts. In this paper, we establish mathematical correspondence between PR and reinforcement learning (RL), and, based on the connection, expand PR to learn constraints as the extrinsic reward in RL. The resulting algorithm is model-agnostic to apply to any DGMs, and is flexible to adapt arbitrary constraints with the model jointly. Experiments on human image generation and templated sentence generation show models with learned knowledge constraints by our algorithm greatly improve over base generative models.

You may want to know: