Mode Collapse in Generative Adversarial Networks: An Overview

Kossale, Youssef; Airaj, Mohammed; Darouichi, Aziz

doi:10.1109/icoa55659.2022.9934291

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If there is mode collapse in the facies construction process, it will lead to mode collapse of the entire model. A commonly used mode collapse evaluation indicator is to plot the data distribution of training samples and generated samples (Lala et al., 2018; K. Liu et al., 2019; Y. Liu et al., 2019). As the MDS maps shown in Figures 6c and 10c, the proposed method can generate diverse hydrogeological facies realizations with similar data distributions as the training samples.…”

Section: Experimental Results and Validationsmentioning

confidence: 99%

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

Cui,

Chen,

Liu

et al. 2024

Water Resources Research

View full text Add to dashboard Cite

Increased availability and quality of surface and subsurface observations provide the chance to improve the perception of hydrological phenomena. An important factor that hinders our understanding of hydrological structures is the characterization of heterogeneous patterns with continuous attributes inside the structures (e.g., porosity, permeability, fluid saturation, etc.). Unlike categorical attributes, continuous attributes convey more realistic characteristics but require more computational resources to characterize such complex earth systems. In this work, we propose a novel deep learning approach for the characterization of complex hydrological realism with continuous attributes based on generative adversarial networks (GANs) and self‐attention mechanism, named SA‐RelayGANs. To address the complexity of heterogeneous hydrological structures, we divide the modeling process into two stages: facies construction stage and property reconstruction stage. In the first stage, we employ an improved GAN with self‐attention mechanism to construct the heterogeneous structures while adhering to hard conditioning constraints. In the second stage, we utilize another GAN with an attribute enhancement term to reconstruct realizations based on the constructed structures and observations. SA‐RelayGANs can successfully predict the statistical distributions of heterogeneous structures with continuous attributes by using limited observations. This study highlights the effectiveness of using GANs to characterize the heterogeneous patterns of hydrological realism and the application over large geoscience fields.

show abstract

Section: Experimental Results and Validationsmentioning

confidence: 99%

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

Cui,

Chen,

Liu

et al. 2024

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…GAN models are susceptible to "mode collapse" [28] which means that they generate samples only from a subset of the expected categories. This can also occur for the models described in this study, where it translates to generating only one or a few of the possible relevant configurations of the system.…”

Section: Post-generation Selection and Relaxationmentioning

confidence: 99%

LoGAN: Local generative adversarial network for novel structure prediction

Kovács,

Heid,

Madsen

2024

Preprint

View full text Add to dashboard Cite

The efficient generation and filtering of candidate structures for new materials is becoming increasingly important as starting points for computational studies. In this work, we introduce an approach to Wasserstein generative adversarial networks for predicting unique crystal and molecular structures. Leveraging translation- and rotation-invariant atom-centered local descriptors address some of the major challenges faced by similar methods. Our models require only small sets of known structures as training data. Furthermore, the approach is able to generate both non-periodic and periodic structures based on local coordination. We showcase the data efficiency and versatility of the LoGAN approach by recovering all stable C5H12O isomers using only 39 C4H10O and C6H14O training examples, as well as all known low-energy SiO2 crystal structures utilizing only 167 training examples of other SiO2 crystal structures. We also introduce a filtration technique to reduce the computational cost of subsequent characterization steps by selecting samples from unique basins on the potential energy surface, which allows to minimize the number of geometry relaxations needed after structure generation. LoGAN thus represents a new, versatile approach to generative modeling of crystal and molecular structures in the low-data regime, and is available open-source.

show abstract

“…Understanding and regulating the relationship between data, variation, and generation process, is essential for the development of efficient GenAI systems [166]. It entails dealing with issues; including dataset biases [167], mode collapse [168], and balancing exploration and exploitation [?]. GenAI systems may generate high-quality, diversified, and realistic samples that correspond with the desired aims and applications by refining the training data, optimizing the generation procedures, and regulating variation [169].…”

Section: A Data Generation Variance and Performance Measuresmentioning

confidence: 99%

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

Hadi,

tashi,

Qureshi

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. Large language models (LLMs) are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, and question-answering. This survey paper provides a comprehensive overview of LLMs, including their history, architecture, training methods, applications, and challenges. The paper begins by discussing the fundamental concepts of generative AI and the architecture of generative pre- trained transformers (GPT). It then provides an overview of the history of LLMs, their evolution over time, and the different training methods that have been used to train them. The paper then discusses the wide range of applications of LLMs, including medical, education, finance, and engineering. It also discusses how LLMs are shaping the future of AI and how they can be used to solve real-world problems. The paper then discusses the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, and computational resource requirements. It also highlights techniques for enhancing the robustness and controllability of LLMs, and addressing bias, fairness, and generation quality issues. Finally, the paper concludes by highlighting the future of LLM research and the challenges that need to be addressed in order to make LLMs more reliable and useful. This survey paper is intended to provide researchers, practitioners, and enthusiasts with a comprehensive understanding of LLMs, their evolution, applications, and challenges. By consolidating the state-of-the-art knowledge in the field, this survey serves as a valuable resource for further advancements in the development and utilization of LLMs for a wide range of real-world applications. The GitHub repo for this project is available at https://github.com/anas-zafar/LLM-Survey</p>

show abstract

Mode Collapse in Generative Adversarial Networks: An Overview

Cited by 9 publications

References 8 publications

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

LoGAN: Local generative adversarial network for novel structure prediction

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

Contact Info

Product

Resources

About