Special Issue on Deep Neural Network Representation and Generative Adversarial Learning

Generative Adversarial Networks (GANs) have proven to be efficient systems for data generation. Their success is achieved by exploiting a minimax learning concept, which has proved to be an effective paradigm in earlier works, such as predictability minimization, in which two networks compete with each other during the learning process. One of the main advantages of GANs over other deep learning methods is their ability to generate new data from noise, as well as their ability to virtually imitate any data distribution. However, generating realistic data using GANs remains a challenge, particularly when specific features are required; for example, constraining the latent aggregate distribution space does not guarantee that the generator will produce an image with a specific attribute. On the other hand, new advancements in deep representation learning (RL) can help improve the learning process in Generative Adversarial Learning (GAL). For instance, RL can help address issues such as dataset bias and network co-adaptation, and identify a set of features that are best suited for a given task.

Despite their obvious advantages and their application to a wide range of domains, GANs have yet to overcome several challenges. They often fail to converge and are very sensitive to parameter and hyper-parameter initialization. Simultaneous learning of a generator and a discriminator network often results in overfitting. Moreover, the generator model is prone to mode collapse, which results in failure to generate data with several variations. Accordingly, new theoretical methods in deep RL and GAL are required to improve the learning process and generalization performance of GANs, as well as to yield new insights into how GANs learn data distributions.

This special issue on Deep Neural Network Representation and Generative Adversarial Learning invites researchers and practitioners to present novel contributions addressing theoretical and practical aspects of deep representation and generative adversarial learning. The special issue will feature a collection of high quality theoretical articles for improving the learning process and the generalization of generative neural networks. State-of-the-art applications based on deep generative adversarial networks are also very welcome. Topics of interest for this special issue include, but are not limited to:

    Representation learning methods and theory;
    Adversarial representation learning for domain adaptation;
    Network interpretability in adversarial learning;
    Adversarial feature learning;
    RL and GAL for data augmentation and class imbalance;
    New GAN models and new GAN learning criteria;
    RL and GAL in classification;
    Adversarial reinforcement learning;
    GANs for noise reduction;
    Recurrent GAN models;
    GANs for imitation learning;
    GANs for image segmentation and image completion;
    GANs for image super-resolution;
    GANs for speech and audio processing
    GANs for object detection;
    GANs for Internet of Things;
    RL and GANs for image and video synthesis;
    RL and GANs for speech and audio synthesis;
    RL and GANs for text to audio or text to image synthesis;
    RL and GANs for inpainting and sketch to image;
    RL and GAL in neural machine translation;
    RL and GANs in other application domains. 

Important Dates:
    30 November 2019 – Submission deadline 
    28 February 2020 – First decision notification
    30 April 2020 – Revised version deadline
    30 June 2020 – Final decision notification
    September 2020 – Publication (papers available online as soon as accepted).

Guest Editors:
Dr Ariel Ruiz-Garcia
Coventry University, UK
Email: ariel.9arcia@gmail.com

Professor Jürgen Schmidhuber
NNAISENSE,
Swiss AI Lab IDSIA,
USI & SUPSI, Switzerland
Email: juergen@idsia.ch

Professor Vasile Palade
Coventry University, UK
Email: vasile.palade@coventry.ac.uk

Dr Clive Cheong Took
Royal Holloway (University of London), UK
Email: Clive.CheongTook@rhul.ac.uk

Professor Danilo Mandic
Imperial College London, UK
Email: d.mandic@imperial.ac.uk

Submission Procedure:
Prospective authors should follow the standard author instructions for Neural Networks, and submit manuscripts online at http://ees.elsevier.com/neunet/. Authors should select “VSI:RL and GANs” when they reach the “Article Type” step and the "Request Editor" step in the submission process.

For any questions related to the special issue please email Dr Ariel Ruiz-Garcia (ariel.9arcia@gmail.com)