paper-with-me

홈 › Papers

Training language GANs from Scratch

2019-05-23 · NeurIPS 2019 12 · Cyprien de Masson d'Autume, Mihaela Rosca, Jack Rae, Shakir Mohamed

Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead practitioners to resort to maximum likelihood pre-training, followed by small amounts of adversarial fine-tuning. The benefits of GAN fine-tuning for language generation are unclear, as the resulting models produce comparable or worse samples than traditional language models. We show it is in fact possible to train a language GAN from scratch -- without maximum likelihood pre-training. We combine existing techniques such as large batch sizes, dense rewards and discriminator regularization to stabilize and improve language GANs. The resulting model, ScratchGAN, performs comparably to maximum likelihood training on EMNLP2017 News and WikiText-103 corpora according to quality and diversity metrics.

📄 PDF Abstract BibTeX arXiv:1905.09922

Code (6)

deepmind/deepmind-research 공식 구현 tf
2023-MindSpore-4/Code10/tree/main/gan mindspore
luke-grassroot/scratchgan tf
shaform/scratchgan-prep tf
urchade/molgen pytorch
yaushian/Unparalleled-Text-Summarization-using-GAN tf

Tasks

DiversityImage GenerationText Generation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance

2022-03-05 · Shiwei Liu, Yuesong Tian, Tianlong Chen, Li Shen

Generative adversarial networks (GANs) have received an upsurging interest since being proposed due to the high quality of the generated data. While achieving increasingly impressive results, the resource demands associa…

Model Compression

Sparse Unbalanced GAN Training with In-Time Over-Parameterization

2021-09-29 · Shiwei Liu, Yuesong Tian, Tianlong Chen, Li Shen

Generative adversarial networks (GANs) have received an upsurging interest since being proposed due to the high quality of the generated data. While GANs achieving increasingly impressive results, the resource demands as…

Model Compression

Language Generation with Recurrent Generative Adversarial Networks without Pre-training

2017-06-05 · Ofir Press, Amir Bar, Ben Bogin, Jonathan Berant 외

Generative Adversarial Networks (GANs) have shown great promise recently in image generation. Training GANs for language generation has proven to be more difficult, because of the non-differentiable nature of generating …

Text Generation

Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation

2021-01-04 · Manel Mateos, Alejandro González, Xavier Sevillano

Generative Adversarial Networks (GANs) are an arrange of two neural networks -- the generator and the discriminator -- that are jointly trained to generate artificial data, such as images, from random inputs. The quality…

Conditional Image GenerationImage GenerationSemantic Segmentation

DAWSON: A Domain Adaptive Few Shot Generation Framework

2020-01-02 · Weixin Liang, Zixuan Liu, Can Liu

Training a Generative Adversarial Networks (GAN) for a new domain from scratch requires an enormous amount of training data and days of training time. To this end, we propose DAWSON, a Domain Adaptive FewShot Generation …

Meta-LearningMusic Generation