This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution ...This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution of a class of data is close to a low-dimensional manifold.GANs mainly accomplish two tasks:manifold learning and probability distribution transformation.The latter can be carried out using the classical OT method.From the OT perspective,the generator computes the OT map,while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution;both can be reduced to a convex geometric optimization process.Furthermore,OT theory discovers the intrinsic collaborative-instead of competitive-relation between the generator and the discriminator,and the fundamental reason for mode collapse.We also propose a novel generative model,which uses an autoencoder(AE)for manifold learning and OT map for probability distribution transformation.This AE–OT model improves the theoretical rigor and transparency,as well as the computational stability and efficiency;in particular,it eliminates the mode collapse.The experimental results validate our hypothesis,and demonstrate the advantages of our proposed model.展开更多
Generative adversarial network(GAN)is one of the most promising methods for unsupervised learning in recent years.GAN works via adversarial training concept and has shown excellent performance in the fields image synt...Generative adversarial network(GAN)is one of the most promising methods for unsupervised learning in recent years.GAN works via adversarial training concept and has shown excellent performance in the fields image synthesis,image super-resolution,video generation,image translation,etc.Compared with classical algorithms,quantum algorithms have their unique advantages in dealing with complex tasks,quantum machine learning(QML)is one of the most promising quantum algorithms with the rapid development of quantum technology.Specifically,Quantum generative adversarial network(QGAN)has shown the potential exponential quantum speedups in terms of performance.Meanwhile,QGAN also exhibits some problems,such as barren plateaus,unstable gradient,model collapse,absent complete scientific evaluation system,etc.How to improve the theory of QGAN and apply it that have attracted some researcher.In this paper,we comprehensively and deeply review recently proposed GAN and QAGN models and their applications,and we discuss the existing problems and future research trends of QGAN.展开更多
针对传统的酒店评论摘要生成模型在生成摘要过程中存在对评论的上下文理解不够充分、并行能力不足和长距离文本依赖缺陷的问题,提出了一种基于TRF-IM(improved mask for transformer)模型的个性化酒店评论摘要生成方法。该方法利用Trans...针对传统的酒店评论摘要生成模型在生成摘要过程中存在对评论的上下文理解不够充分、并行能力不足和长距离文本依赖缺陷的问题,提出了一种基于TRF-IM(improved mask for transformer)模型的个性化酒店评论摘要生成方法。该方法利用Transformer译码器结构对评论摘要任务进行建模,通过改进其结构中的掩码方式,使得源评论内容都能够更好地学习到上下文语义信息;同时引入了用户类型的个性化词特征信息,使其生成高质量且满足用户需求的个性化酒店评论摘要。实验结果表明,该模型相比传统模型在ROUGE指标上取得了更高的分数,生成了高质量的个性化酒店评论摘要。展开更多
基金the National Natural Science Foundation of China(61936002,61772105,61432003,61720106005,and 61772379)US National Science Foundation(NSF)CMMI-1762287 collaborative research“computational framework for designing conformal stretchable electronics,Ford URP topology optimization of cellular mesostructures’nonlinear behaviors for crash safety,”NSF DMS-1737812 collaborative research“ATD:theory and algorithms for discrete curvatures on network data from human mobility and monitoring.”。
文摘This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution of a class of data is close to a low-dimensional manifold.GANs mainly accomplish two tasks:manifold learning and probability distribution transformation.The latter can be carried out using the classical OT method.From the OT perspective,the generator computes the OT map,while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution;both can be reduced to a convex geometric optimization process.Furthermore,OT theory discovers the intrinsic collaborative-instead of competitive-relation between the generator and the discriminator,and the fundamental reason for mode collapse.We also propose a novel generative model,which uses an autoencoder(AE)for manifold learning and OT map for probability distribution transformation.This AE–OT model improves the theoretical rigor and transparency,as well as the computational stability and efficiency;in particular,it eliminates the mode collapse.The experimental results validate our hypothesis,and demonstrate the advantages of our proposed model.
基金This work is supported by the National Natural Science Foundation of China(No.61572086,No.61402058)the Key Research and Development Project of Sichuan Province(Nos.20ZDYF2324,2019ZYD027 and 2018TJPT0012)+3 种基金the Innovation Team of Quantum Security Communication of Sichuan Province(No.17TD0009)the Academic and Technical Leaders Training Funding Support Projects of Sichuan Province(No.2016120080102643)the Application Foundation Project of Sichuan Province(No.2017JY0168)the Science and Technology Support Project of Sichuan Province(Nos.2018GZ0204 and 2016FZ0112).
文摘Generative adversarial network(GAN)is one of the most promising methods for unsupervised learning in recent years.GAN works via adversarial training concept and has shown excellent performance in the fields image synthesis,image super-resolution,video generation,image translation,etc.Compared with classical algorithms,quantum algorithms have their unique advantages in dealing with complex tasks,quantum machine learning(QML)is one of the most promising quantum algorithms with the rapid development of quantum technology.Specifically,Quantum generative adversarial network(QGAN)has shown the potential exponential quantum speedups in terms of performance.Meanwhile,QGAN also exhibits some problems,such as barren plateaus,unstable gradient,model collapse,absent complete scientific evaluation system,etc.How to improve the theory of QGAN and apply it that have attracted some researcher.In this paper,we comprehensively and deeply review recently proposed GAN and QAGN models and their applications,and we discuss the existing problems and future research trends of QGAN.
文摘针对传统的酒店评论摘要生成模型在生成摘要过程中存在对评论的上下文理解不够充分、并行能力不足和长距离文本依赖缺陷的问题,提出了一种基于TRF-IM(improved mask for transformer)模型的个性化酒店评论摘要生成方法。该方法利用Transformer译码器结构对评论摘要任务进行建模,通过改进其结构中的掩码方式,使得源评论内容都能够更好地学习到上下文语义信息;同时引入了用户类型的个性化词特征信息,使其生成高质量且满足用户需求的个性化酒店评论摘要。实验结果表明,该模型相比传统模型在ROUGE指标上取得了更高的分数,生成了高质量的个性化酒店评论摘要。
