Summary of A Non-negative Vae:the Generalized Gamma Belief Network, by Zhibin Duan et al.
A Non-negative VAE:the Generalized Gamma Belief Network
by Zhibin Duan, Tiansheng Wen, Muyao Wang, Bo Chen, Mingyuan Zhou
First submitted to arxiv on: 6 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel extension to the gamma belief network (GBN), a deep topic model, by introducing the generalized gamma belief network (Generalized GBN). The original linear generative model of GBN is limited in its expressiveness and applicability. To overcome this limitation, the authors propose an upward-downward Weibull inference network to approximate the posterior distribution of latent variables. The parameters of both the generative model and the inference network are jointly trained within a variational inference framework. Compared to Gaussian variational autoencoders serving as baselines, the Generalized GBN is evaluated on expressivity and disentangled representation learning tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers extend the gamma belief network (GBN) to create a more expressive model that can uncover hidden patterns in text data. The original linear model was limited, so they developed an upward-downward Weibull inference network to help learn about these patterns. They trained both models together and tested them against other popular methods. |
Keywords
» Artificial intelligence » Generative model » Inference » Representation learning
