Timezone: »

 
Poster
Deep Generative Models with Learnable Knowledge Constraints
Zhiting Hu · Zichao Yang · Russ Salakhutdinov · LIANHUI Qin · Xiaodan Liang · Haoye Dong · Eric Xing

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 210 #32
in Wed Poster Session A »

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.

Keywords: Generative Models
[ Paper] 

Author Information

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)

More from the Same Authors