Latent Diffusion Energy-Based Model for Interpretable Text Modeling

Song-Chun Zhu, Ying Wu, Bo Pang, Ruiqi Gao, Yixin Zhu, Xiaojian Ma, Peiyu Yu, Sirui Xie, Baoxiong Jia

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• yupeiyu98/latent-diffusion-ebm — marked official in Papers with Code; named in the paper
• yupeiyu98/ldebm — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built upon it have made interesting attempts aiming at the interpretability of text modeling. However, latent space EBMs also inherit some flaws from EBMs in data space; the degenerate MCMC sampling quality in practice can lead to poor generation quality and instability in training, especially on data with complex latent structures. Inspired by the recent efforts that leverage diffusion recovery likelihood learning as a cure for the sampling issue, we introduce a novel symbiosis between the diffusion models and latent space EBMs in a variational learning framework, coined as the latent diffusion energy-based model. We develop a geometric clustering-based regularization jointly with the information bottleneck to further improve the quality of the learned latent space. Experiments on several challenging tasks demonstrate the superior performance of our model on interpretable text modeling over strong counterparts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.05895")
get_code_for_paper("2206.05895")
have("2206.05895")

Connect an agent — have() is free.