.png){kind=icon}
.png){kind=icon}
Return
PaddingFlow: Improving normalizing flows with padding-dimensional noise
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2025.130651.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: (1) If the target distribution is manifold, due to the mismatch between the dimensions of the latent target distribution and the data distribution, flow-based models might perform badly. (2) Discrete data might make flow-based models collapse into a degenerate mixture of point masses. To sidestep such two issues, we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. To implement PaddingFlow, only the dimension of normalizing flows needs to be modified. Thus, our method is easy to implement and computationally cheap. Moreover, the padding-dimensional noise is only added to the padding dimension, which means that PaddingFlow can dequantize without changing data distributions. After implementing existing dequantization methods, the original data distributions are changed, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for Variational Autoencoder (VAE) models, and the Inverse Kinematics (IK) experiments which are conditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper, which means PaddingFlow is widely suitable for various tasks. The code is available at: https://github.com/AdamQLMeng/PaddingFlow .
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available