Generative Cooperative Networks for Natural Language Generation

• URL: http://arxiv.org/abs/2201.12320v1
• Date: Fri, 28 Jan 2022 18:36:57 GMT
• Title: Generative Cooperative Networks for Natural Language Generation
• Authors: Sylvain Lamprier and Thomas Scialom and Antoine Chaffin and Vincent Claveau and Ewa Kijak and Jacopo Staiano and Benjamin Piwowarski
• Abstract summary: We introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts. We give theoretical guarantees of convergence for our approach, and study various efficient decoding schemes to empirically achieve state-of-the-art results in two main NLG tasks.
• Score: 25.090455367573988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation. However, for discrete outputs such as language, optimizing GANs remains an open problem with many instabilities, as no gradient can be properly back-propagated from the discriminator output to the generator parameters. An alternative is to learn the generator network via reinforcement learning, using the discriminator signal as a reward, but such a technique suffers from moving rewards and vanishing gradient problems. Finally, it often falls short compared to direct maximum-likelihood approaches. In this paper, we introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts for the task at hand. We give theoretical guarantees of convergence for our approach, and study various efficient decoding schemes to empirically achieve state-of-the-art results in two main NLG tasks.

Related papers

• DiffSG: A Generative Solver for Network Optimization with Diffusion Model [75.27274046562806]
  Diffusion generative models can consider a broader range of solutions and exhibit stronger generalization by learning parameters. We propose a new framework, which leverages intrinsic distribution learning of diffusion generative models to learn high-quality solutions.
  arXiv  Detail & Related papers  (2024-08-13T07:56:21Z)
• Intelligent Hybrid Resource Allocation in MEC-assisted RAN Slicing Network [72.2456220035229]
  We aim to maximize the SSR for heterogeneous service demands in the cooperative MEC-assisted RAN slicing system. We propose a recurrent graph reinforcement learning (RGRL) algorithm to intelligently learn the optimal hybrid RA policy.
  arXiv  Detail & Related papers  (2024-05-02T01:36:13Z)
• Efficient generative adversarial networks using linear additive-attention Transformers [0.8287206589886879]
  We present LadaGAN, an efficient generative adversarial network that is built upon a novel Transformer block named Ladaformer. LadaGAN consistently outperforms existing convolutional and Transformer GANs on benchmark datasets at different resolutions.
  arXiv  Detail & Related papers  (2024-01-17T21:08:41Z)
• GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model [69.71629949747884]
  Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data. In this work, we propose a novel algorithm named GE-AdvGAN to enhance the transferability of adversarial samples.
  arXiv  Detail & Related papers  (2024-01-11T16:43:16Z)
• Prompt Optimization via Adversarial In-Context Learning [51.18075178593142]
  adv-ICL is implemented as a two-player game between a generator and a discriminator. The generator tries to generate realistic enough output to fool the discriminator. We show that adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques.
  arXiv  Detail & Related papers  (2023-12-05T09:44:45Z)
• A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancy [2.966338139852619]
  Generative adversarial networks (GANs) and variational autoencoders (VAEs) are two of the most prominent and widely studied generative models. We employ a Bayesian non-parametric (BNP) approach to merge GANs and VAEs. By fusing the discriminative power of GANs with the reconstruction capabilities of VAEs, our novel model achieves superior performance in various generative tasks.
  arXiv  Detail & Related papers  (2023-08-27T08:58:31Z)
• DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion [2.458437232470188]
  Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques. We propose a novel approach for class-conditional image generation using GANs called DuDGAN, which incorporates a dual diffusion-based noise injection process. Our method outperforms state-of-the-art conditional GAN models for image generation in terms of performance.
  arXiv  Detail & Related papers  (2023-05-24T07:59:44Z)
• To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs [31.040350519448342]
  Language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. We show that our SelfGAN framework, built on this cooperative principle, outperforms Teacher Forcing and obtains state-of-the-art results on two challenging tasks.
  arXiv  Detail & Related papers  (2021-06-11T13:04:42Z)
• MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains [77.46963293257912]
  We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. We show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods.
  arXiv  Detail & Related papers  (2021-04-28T13:10:56Z)
• Autoencoding Generative Adversarial Networks [0.0]
  I propose a four-network model which learns a mapping between a specified latent space and a given sample space. The AEGAN technique offers several improvements to typical GAN training, including training stabilization, mode-collapse prevention, and permitting the directversa between real samples.
  arXiv  Detail & Related papers  (2020-04-11T19:51:04Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.