Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.7
Journals
Entropy
Special Issues
Deep Generative Modeling: Theory and Applications
entropy-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Entropy Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Deep Generative Modeling: Theory and Applications

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".

Deadline for manuscript submissions: 31 May 2024 | Viewed by 10891

Special Issue Editor

Dr. Jakub Tomczak

E-Mail Website
Guest Editor
Department of Mathematics and Computer Science, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands
Interests: generative artificial intelligence; deep generative modeling; deep learning; probabilistic modeling; Bayesian inference; information theory

Special Issue Information

Dear Colleagues,

The field of generative artificial intelligence tackles the problem of formulating AI systems by combining probabilistic modeling and deep learning. Generative AI goes beyond the typical predictive modeling and brings together supervised learning and unsupervised learning by utilizing the generative perspective in perceiving the surrounding world. It assumes that each phenomenon is driven by an underlying generative process that defines a joint distribution over random variables and their stochastic interactions, and, typically, it is parameterized using a deep neural network.

There are two distinct traits of generative AI. First, the principled manner of modeling stochastic dependencies using probability theory ensures rigorous formulation and prevents potential flaws in reasoning. Moreover, probability theory provides a unified framework where the likelihood function plays a crucial role in quantifying uncertainty and defining objective functions. Second, the application of deep neural networks allows rich and flexible parameterization of distributions. As a result, generative AI is used for the formulation of deep generative models that can be used for defining generative processes, synthesizing new data, and quantifying uncertainty. The theoretical aspects of generative AI are reinforced by multiple applications in life sciences (biology, biochemistry) and molecular sciences (chemistry, physics), and problems ranging from signal processing (e.g., data compression) to self-driving cars, smart devices, and smart apps (e.g., chatbots, art generation).

This Special Issue aims to provide a forum for the presentation of new and improved deep generative models as well as their applications. In particular, theoretical considerations about deep generative modeling (e.g., an analysis with the help of statistical tools based on information theory) and real-life applications (e.g., in life sciences or molecular sciences) fall within the scope of this Special Issue.

Dr. Jakub Tomczak
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • variational auto-encoders
  • diffusion-based generative models
  • flow-based generative models
  • autoregressive generative models
  • energy-based models
  • hybrid modeling
  • neural compression
  • AI4Science
  • life sciences
  • molecular sciences

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

38 pages, 19811 KiB  
Article
Multi-Modal Latent Diffusion
by Mustapha Bounoua, Giulio Franzese and Pietro Michiardi
Entropy 2024, 26(4), 320; https://doi.org/10.3390/e26040320 - 05 Apr 2024
Viewed by 428
Abstract
Multimodal datasets are ubiquitous in modern applications, and multimodal Variational Autoencoders are a popular family of models that aim to learn a joint representation of different modalities. However, existing approaches suffer from a coherence–quality tradeoff in which models with good generation quality lack [...] Read more.
Multimodal datasets are ubiquitous in modern applications, and multimodal Variational Autoencoders are a popular family of models that aim to learn a joint representation of different modalities. However, existing approaches suffer from a coherence–quality tradeoff in which models with good generation quality lack generative coherence across modalities and vice versa. In this paper, we discuss the limitations underlying the unsatisfactory performance of existing methods in order to motivate the need for a different approach. We propose a novel method that uses a set of independently trained and unimodal deterministic autoencoders. Individual latent variables are concatenated into a common latent space, which is then fed to a masked diffusion model to enable generative modeling. We introduce a new multi-time training method to learn the conditional score network for multimodal diffusion. Our methodology substantially outperforms competitors in both generation quality and coherence, as shown through an extensive experimental campaign. Full article
(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
►▼ Show Figures

Figure 1

24 pages, 1977 KiB  
Article
Semi-Supervised Variational Autoencoders for Out-of-Distribution Generation
by Frantzeska Lavda and Alexandros Kalousis
Entropy 2023, 25(12), 1659; https://doi.org/10.3390/e25121659 - 14 Dec 2023
Viewed by 936
Abstract
Humans are able to quickly adapt to new situations, learn effectively with limited data, and create unique combinations of basic concepts. In contrast, generalizing out-of-distribution (OOD) data and achieving combinatorial generalizations are fundamental challenges for machine learning models. Moreover, obtaining high-quality labeled examples [...] Read more.
Humans are able to quickly adapt to new situations, learn effectively with limited data, and create unique combinations of basic concepts. In contrast, generalizing out-of-distribution (OOD) data and achieving combinatorial generalizations are fundamental challenges for machine learning models. Moreover, obtaining high-quality labeled examples can be very time-consuming and expensive, particularly when specialized skills are required for labeling. To address these issues, we propose BtVAE, a method that utilizes conditional VAE models to achieve combinatorial generalization in certain scenarios and consequently to generate out-of-distribution (OOD) data in a semi-supervised manner. Unlike previous approaches that use new factors of variation during testing, our method uses only existing attributes from the training data but in ways that were not seen during training (e.g., small objects of a specific shape during training and large objects of the same shape during testing). Full article
(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
►▼ Show Figures

Figure 1

22 pages, 18479 KiB  
Article
Diffusion Probabilistic Modeling for Video Generation
by Ruihan Yang, Prakhar Srivastava and Stephan Mandt
Entropy 2023, 25(10), 1469; https://doi.org/10.3390/e25101469 - 20 Oct 2023
Cited by 106 | Viewed by 3020
Abstract
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end [...] Read more.
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare this approach against six baselines on four datasets involving natural and simulation-based videos. We find significant improvements in terms of perceptual quality and probabilistic frame forecasting ability for all datasets. Full article
(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
►▼ Show Figures

Figure 1

18 pages, 4606 KiB  
Article
Learning Energy-Based Models in High-Dimensional Spaces with Multiscale Denoising-Score Matching
by Zengyi Li, Yubei Chen and Friedrich T. Sommer
Entropy 2023, 25(10), 1367; https://doi.org/10.3390/e25101367 - 22 Sep 2023
Viewed by 1408
Abstract
Energy-based models (EBMs) assign an unnormalized log probability to data samples. This functionality has a variety of applications, such as sample synthesis, data denoising, sample restoration, outlier detection, Bayesian reasoning and many more. But, the training of EBMs using standard maximum likelihood is [...] Read more.
Energy-based models (EBMs) assign an unnormalized log probability to data samples. This functionality has a variety of applications, such as sample synthesis, data denoising, sample restoration, outlier detection, Bayesian reasoning and many more. But, the training of EBMs using standard maximum likelihood is extremely slow because it requires sampling from the model distribution. Score matching potentially alleviates this problem. In particular, denoising-score matching has been successfully used to train EBMs. Using noisy data samples with one fixed noise level, these models learn fast and yield good results in data denoising. However, demonstrations of such models in the high-quality sample synthesis of high-dimensional data were lacking. Recently, a paper showed that a generative model trained by denoising-score matching accomplishes excellent sample synthesis when trained with data samples corrupted with multiple levels of noise. Here we provide an analysis and empirical evidence showing that training with multiple noise levels is necessary when the data dimension is high. Leveraging this insight, we propose a novel EBM trained with multiscale denoising-score matching. Our model exhibits a data-generation performance comparable to state-of-the-art techniques such as GANs and sets a new baseline for EBMs. The proposed model also provides density information and performs well on an image-inpainting task. Full article
(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
►▼ Show Figures

Figure 1

30 pages, 6120 KiB  
Article
How Much Is Enough? A Study on Diffusion Times in Score-Based Generative Models
by Giulio Franzese, Simone Rossi, Lixuan Yang, Alessandro Finamore, Dario Rossi, Maurizio Filippone and Pietro Michiardi
Entropy 2023, 25(4), 633; https://doi.org/10.3390/e25040633 - 07 Apr 2023
Cited by 15 | Viewed by 3155
Abstract
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have started to lay down a theoretical foundation for these models, a detailed understanding of the role of [...] Read more.
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have started to lay down a theoretical foundation for these models, a detailed understanding of the role of the diffusion time T is still lacking. Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution; however, a smaller value of T should be preferred for a better approximation of the score-matching objective and higher computational efficiency. Starting from a variational interpretation of diffusion models, in this work we quantify this trade-off and suggest a new method to improve quality and efficiency of both training and sampling, by adopting smaller diffusion times. Indeed, we show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process. Empirical results support our analysis; for image data, our method is competitive with regard to the state of the art, according to standard sample quality metrics and log-likelihood. Full article
(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop