Timezone: »
Latent space energy-based model has drawn growing interest in generative modelling in recent years. Fueled by its flexibility in formulation and strong modelling power of the latent space, recent works have been built upon it aiming at the interpretability of text modeling. However, latent space energy-based model also inherits some of the flaws of energy-based model: the degenerated MCMC sampling quality in practice can lead to not only poor generation quality but also instability in training, especially on data with complex latent structures. On another front, diffusion probabilistic models, inspired by non-equilibrium thermodynamics, have provided an appealing methodology that breaks down the heavy generation process and eases the burden of sampling. In this work, we show how the philosophy of diffusion probabilistic models becomes a cure for the vanilla latent space energy-based model, namely the latent diffusion energy-based model. Such a symbiosis between these classical models offers the best of both worlds: it learns a well-structured and meaningful latent space; it can be flexibly extended to scenarios where data labels are available as supervision signal; it demonstrates superior performance on interpretable text modelling over strong baselines.
Author Information
Peiyu Yu (University of California, Los Angeles)
Sirui Xie (UCLA)
Xiaojian Ma (Tsinghua University)
Xiaojian Ma is a senior undergraduate student at Tsinghua University and will be an incoming graduate student at the University of California, Los Angeles working with Prof. Song-chun Zhu. Previously he has been a visiting student at the National University of Singapore, with Prof. Gim Hee Lee. He also spends time at Tencent AI Lab, mentored by Dr. Wenbing Huang. His research interest including machine learning in general (statistical learning, learning theory, and reinforcement learning) and its application in robotics (imitation learning, optimal control, manipulation, grasping and multimodel sensing). Some of his research has been accepted as full papers or workshop papers to top-tier machine learning and robotics conferences as AAAI/ICRA/IROS/CVPR.
Baoxiong Jia (UCLA)
Bo Pang (University of California Los Angeles)
Ruiqi Gao (UCLA)
Yixin Zhu (Peking University)
Song-Chun Zhu (UCLA)
Ying Nian Wu (UCLA)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Latent Diffusion Energy-Based Model for Interpretable Text Modelling »
Dates n/a. Room None
More from the Same Authors
-
2022 Poster: COAT: Measuring Object Compositionality in Emergent Representations »
Sirui Xie · Ari Morcos · Song-Chun Zhu · Shanmukha Ramakrishna Vedantam -
2022 Spotlight: COAT: Measuring Object Compositionality in Emergent Representations »
Sirui Xie · Ari Morcos · Song-Chun Zhu · Shanmukha Ramakrishna Vedantam -
2021 : [12:02 - 12:47 PM UTC] Invited Talk 1: Explainable AI: How Machines Gain Justified Trust from Humans »
Song-Chun Zhu -
2021 Workshop: ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI »
Quanshi Zhang · Tian Han · Lixin Fan · Zhanxing Zhu · Hang Su · Ying Nian Wu -
2021 Poster: Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification »
Bo Pang · Ying Nian Wu -
2021 Spotlight: Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification »
Bo Pang · Ying Nian Wu -
2020 Poster: Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning »
Qing Li · Siyuan Huang · Yining Hong · Yixin Chen · Ying Nian Wu · Song-Chun Zhu -
2018 Poster: Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction »
Siyuan Qi · Baoxiong Jia · Song-Chun Zhu -
2018 Oral: Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction »
Siyuan Qi · Baoxiong Jia · Song-Chun Zhu