Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive...Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive framework based on generative adversarial network(GAN)for characterizing pore structure properties of shale,which incorporates image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation.Using real 2D and 3D shale images,the framework was assessed through correlation function,entropy,porosity,pore size distribution,and permeability.The application results show that this framework enables the enhancement of 3D low-resolution digital cores by a scale factor of 8,without paired shale images,effectively reconstructing the unresolved fine-scale pores under a low resolution,rather than merely denoising,deblurring,and edge clarification.The trained GAN-based segmentation model effectively improves manual multi-mineral segmentation results,resulting in a strong resemblance to real samples in terms of pore size distribution and permeability.This framework significantly improves the characterization of complex shale microstructures and can be expanded to other heterogeneous porous media,such as carbonate,coal,and tight sandstone reservoirs.展开更多
In this study,cylindrical sandstone samples were imaged by CT scanning technique,and the pore structure images of sandstone samples were analyzed and generated by combining with StyleGAN2-ADA generative adversarial ne...In this study,cylindrical sandstone samples were imaged by CT scanning technique,and the pore structure images of sandstone samples were analyzed and generated by combining with StyleGAN2-ADA generative adversarial network(GAN)model.Firstly,nine small column samples with a diameter of 4 mm were drilled from sandstone samples with a diameter of 2.5 cm,and their CT scanning results were preprocessed.Because the change between adjacent slices was little,using all slices directly may lead to the problem of pattern collapse in the process of model generation.In order to solve this problem,one slice was selected as training data every 30 slices,and the diversity of slices was verified by calculating the LPIPS values of these slices.The results showed that the strategy of selecting one slice every 30 slices could effectively improve the diversity of images generated by the model and avoid the phenomenon of pattern collapse.Through this process,a total of 295 discontinuous two-dimensional slices were generated for the generation and segmentation analysis of sandstone pore structures.This study can provide effective data support for accurate segmentation of porous medium structures,and simultaneously improves the stability and diversity of generative adversarial network under the condition of small samples.展开更多
Heat dissipation performance is critical to the design of high-end equipment,such as integrated chips and high-precision machine tools.Owing to the advantages of artificial intelligence in solving complex tasks involv...Heat dissipation performance is critical to the design of high-end equipment,such as integrated chips and high-precision machine tools.Owing to the advantages of artificial intelligence in solving complex tasks involving a large number of variables,researchers have exploited deep learning to expedite the optimization of material properties,such as the heat dissipation of solid isotropic materials with penalization(SIMP).However,because the approach is limited by discrete datasets and labeled training forms,ensuring the continuous adaptation of the condition domain and maintaining the stability of the design structure remain major challenges in the current intelligent design methodology for thermally conductive structures.In this study,we propose an innovative intelligent design fram-ework integrating Conditional Deep Convolutional Generative Adversarial Networks(CDCGAN)with SIMP,capable of creating topology structures that meet prescribed thermal conduction performance.This proposed design strategy significantly reduces the computational time required to solve symmetric and random heat sink problems compared with existing design approaches and is approximately 98%faster than standard SIMP methods and 55.5%faster than conventional deep-learning-based methods.In addition,we benchmarked the design performance of the proposed framework against theoretical structural designs via experimental measurements.We observed a 50.1%reduction in the average temperature and a 28.2%reduction in the highest temperature in our designed topology compared with those theoretical structure designs.展开更多
We introduce Hair-GAN,an architecture of generative adversarial networks,to recover the 3D hair structure from a single image.The goal of our networks is to build a parametric transformation from 2D hair maps to 3D ha...We introduce Hair-GAN,an architecture of generative adversarial networks,to recover the 3D hair structure from a single image.The goal of our networks is to build a parametric transformation from 2D hair maps to 3D hair structure.The 3D hair structure is represented as a 3D volumetric field which encodes both the occupancy and the orientation information of the hair strands.Given a single hair image,we first align it with a bust model and extract a set of 2D maps encoding the hair orientation information in 2D,along with the bust depth map to feed into our Hair-GAN.With our generator network,we compute the 3D volumetric field as the structure guidance for the final hair synthesis.The modeling results not only resemble the hair in the input image but also possesses many vivid details in other views.The efficacy of our method is demonstrated by using a variety of hairstyles and comparing with the prior art.展开更多
This paper presents a deep learning-based topology optimization method for the joint design of material layout and fiber orientation in continuous fiber-reinforced composite structure(CFRCS).The proposed method mainly...This paper presents a deep learning-based topology optimization method for the joint design of material layout and fiber orientation in continuous fiber-reinforced composite structure(CFRCS).The proposed method mainly includes three steps:(1)a ResUNet-involved generative and adversarial network(ResUNet-GAN)is developed to establish the end-to-end mapping from structural design parameters to fiber-reinforced composite optimized structure,and a fiber orientation chromatogram is presented to represent continuous fiber angles;(2)to avoid the local optimum problem,the independent continuous mapping method(ICM method)considering the improved principal stress orientation interpolated continuous fiber angle optimization(PSO-CFAO)strategy is utilized to construct CFRCS topology optimization dataset;(3)the well-trained ResUNet-GAN is deployed to design the optimal structural material distribution together with the corresponding continuous fiber orientations.Numerical simulations for benchmark structure verify that the proposed method greatly improves the design efficiency of CFRCS along with high design accuracy.Furthermore,the CFRCS topology configuration designed by ResUNet-GAN is fabricated by additive manufacturing.Compression experiments of the specimens show that both the stiffness structure and peak load of the CFRCS topology configuration designed by the proposed method have significantly enhanced.The proposed deep learning-based topology optimization method will provide great flexibility in CFRCS for engineering applications.展开更多
In China,traditional village layouts are dynamic,harmoniously integrated with the natural environment,and rich in unique cultural characteristics.However,rapidly constructed villages often lack professional design,res...In China,traditional village layouts are dynamic,harmoniously integrated with the natural environment,and rich in unique cultural characteristics.However,rapidly constructed villages often lack professional design,resulting in overly simple layouts and causing the villages to lose their traditional characteristics.Artiflcial intelligence holds the potential to alleviate this speciflc challenge.This study employs CGAN to generate comprehensive village layouts based on archetypal traditional villages,while also exploring parameters and network architectures to enhance result quality.The research address on traditional villages in southwestern Hubei,reflning generative factors,introducing image-based geographic scales,and employing machine vision to address data scarcity.The key flndings of this study includes:1)The research explores a class of AI-generated evaluation metrics suitable for village layout generation.2)It conflrms that the combination of the Unet_256 generator with the LSGAN architecture yields the best results in image generation.3)It is observed that the optimal generation results are achieved when the equivalent geographic scale of the image is 150 m×150 m.The study validates that GANs can be effectively applied in the village layout,producing layout results that incorporate traditional local experiences.This provides a novel approach to village layout.展开更多
The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera im...The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.展开更多
To address the problems of lack of high-frequency information and texture details and unstable training in superresolution generative adversarial net-works,this paper optimizes the generator and discriminator based on...To address the problems of lack of high-frequency information and texture details and unstable training in superresolution generative adversarial net-works,this paper optimizes the generator and discriminator based on the SRGAN model.First,the residual dense block is used as the basic structural unit of the gen-erator to improve the network’s feature extraction capability.Second,enhanced lightweight coordinate attention is incorporated to help the network more precisely concentrate on high-frequency location information,thereby allowing the gener-ator to produce more realistic image reconstruction results.Then,we propose a symmetric and efficient pyramidal segmentation attention discriminator network in which the attention mechanism is capable of derivingfiner-grained multiscale spatial information and creating long-term dependencies between multiscale chan-nel attentions,thus enhancing the discriminative ability of the network.Finally,a Charbonnier loss function and a gradient variance loss function with improved robustness are used to better realize the image’s texture structure and enhance the model’s stability.Thefindings from the experiments reveal that the reconstructed image quality enhances the average peak signal-to-noise ratio(PSNR)by 1.59 dB and the structural similarity index(SSIM)by 0.045 when compared to SRGAN on the three test sets.Compared with the state-of-the-art methods,the reconstructed images have a clearer texture structure,richer high-frequency details,and better visual effects.展开更多
2D patterned hollow structures have emerged as advanced materials with exceptional mechanical properties and lightweight characteristics,making them ideal for high-performance applications in aerospace and automotive ...2D patterned hollow structures have emerged as advanced materials with exceptional mechanical properties and lightweight characteristics,making them ideal for high-performance applications in aerospace and automotive industries.However,optimizing their structural design to achieve uniform stress distribution and minimize stress concentration remains a significant challenge due to the complex interplay between geometric patterns and mechanical performance.In this study,we develop an integrated framework combining conditional generative adversarial networks(cGANs)and deep Q-networks(DQNs)to predict and optimize the stress fields of 2D-PHS.We generated a comprehensive dataet comprising 1000 samples across five distinct density classes using a custom grid pattern generation algorithm,ensuring a wide range of structural variations.The cGAN accurately predicts stress distributions,achieving a high correlation with finite element analysis(FEA)results while reducing computational time from approximately 40 s(FEA)to just 1-2 s per prediction.Concurrently,the DQN optimizes design parameters through scaling and rotation operations,enhancing structural performance based on predicted stress metrics.Our approach resulted in a 4.3%improvement in average stress uniformity and a 23.1%reduction in maximum stress concentration.These improvements were validated through FEA simulations and experimental tensile tests on 3D-printed thermoplastic polyurethane samples.The tensile strength of the optimized samples increased from an initial average of 5.9-6.6 MPa under 100%strain,demonstrating enhanced mechanical resilience.This study demonstrates the efficacy of combining advanced AI techniques for rapid and precise material design optimization,providing a scalable and cost-effective solution for developing superior lightweight materials with tailored mechanical properties for critical engineering applications.展开更多
Network embedding which aims to embed a given network into a low-dimensional vector space has been proved effective in various network analysis and mining tasks such as node classification,link prediction and network ...Network embedding which aims to embed a given network into a low-dimensional vector space has been proved effective in various network analysis and mining tasks such as node classification,link prediction and network visualization.The emerging network embedding methods have shifted of emphasis in utilizing mature deep learning models.The neural-network based network embedding has become a mainstream solution because of its high eficiency and capability of preserv-ing the nonlinear characteristics of the network.In this paper,we propose Adversarial Network Embedding using Structural Similarity(ANESS),a novel,versatile,low-complexity GAN-based network embedding model which utilizes the inherent vertex-to-vertex structural similarity attribute of the network.ANESS learns robustness and ffective vertex embeddings via a adversarial training procedure.Specifically,our method aims to exploit the strengths of generative adversarial networks in generating high-quality samples and utilize the structural similarity identity of vertexes to learn the latent representations of a network.Meanwhile,ANESS can dynamically update the strategy of generating samples during each training iteration.The extensive experiments have been conducted on the several benchmark network datasets,and empirical results demon-strate that ANESS significantly outperforms other state-of-theart network embedding methods.展开更多
基金Supported by the National Natural Science Foundation of China(U23A20595,52034010,52288101)National Key Research and Development Program of China(2022YFE0203400)+1 种基金Shandong Provincial Natural Science Foundation(ZR2024ZD17)Fundamental Research Funds for the Central Universities(23CX10004A).
文摘Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive framework based on generative adversarial network(GAN)for characterizing pore structure properties of shale,which incorporates image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation.Using real 2D and 3D shale images,the framework was assessed through correlation function,entropy,porosity,pore size distribution,and permeability.The application results show that this framework enables the enhancement of 3D low-resolution digital cores by a scale factor of 8,without paired shale images,effectively reconstructing the unresolved fine-scale pores under a low resolution,rather than merely denoising,deblurring,and edge clarification.The trained GAN-based segmentation model effectively improves manual multi-mineral segmentation results,resulting in a strong resemblance to real samples in terms of pore size distribution and permeability.This framework significantly improves the characterization of complex shale microstructures and can be expanded to other heterogeneous porous media,such as carbonate,coal,and tight sandstone reservoirs.
文摘In this study,cylindrical sandstone samples were imaged by CT scanning technique,and the pore structure images of sandstone samples were analyzed and generated by combining with StyleGAN2-ADA generative adversarial network(GAN)model.Firstly,nine small column samples with a diameter of 4 mm were drilled from sandstone samples with a diameter of 2.5 cm,and their CT scanning results were preprocessed.Because the change between adjacent slices was little,using all slices directly may lead to the problem of pattern collapse in the process of model generation.In order to solve this problem,one slice was selected as training data every 30 slices,and the diversity of slices was verified by calculating the LPIPS values of these slices.The results showed that the strategy of selecting one slice every 30 slices could effectively improve the diversity of images generated by the model and avoid the phenomenon of pattern collapse.Through this process,a total of 295 discontinuous two-dimensional slices were generated for the generation and segmentation analysis of sandstone pore structures.This study can provide effective data support for accurate segmentation of porous medium structures,and simultaneously improves the stability and diversity of generative adversarial network under the condition of small samples.
基金Supported by National Natural Science Foundation of China(Grant Nos.52222508 and 52335011)。
文摘Heat dissipation performance is critical to the design of high-end equipment,such as integrated chips and high-precision machine tools.Owing to the advantages of artificial intelligence in solving complex tasks involving a large number of variables,researchers have exploited deep learning to expedite the optimization of material properties,such as the heat dissipation of solid isotropic materials with penalization(SIMP).However,because the approach is limited by discrete datasets and labeled training forms,ensuring the continuous adaptation of the condition domain and maintaining the stability of the design structure remain major challenges in the current intelligent design methodology for thermally conductive structures.In this study,we propose an innovative intelligent design fram-ework integrating Conditional Deep Convolutional Generative Adversarial Networks(CDCGAN)with SIMP,capable of creating topology structures that meet prescribed thermal conduction performance.This proposed design strategy significantly reduces the computational time required to solve symmetric and random heat sink problems compared with existing design approaches and is approximately 98%faster than standard SIMP methods and 55.5%faster than conventional deep-learning-based methods.In addition,we benchmarked the design performance of the proposed framework against theoretical structural designs via experimental measurements.We observed a 50.1%reduction in the average temperature and a 28.2%reduction in the highest temperature in our designed topology compared with those theoretical structure designs.
基金This work is partially supported by the National Key Research&Development Program of China(2018YFE0100900)the China Young 1000 Talent Programthe Fundamental Research Funds for the Central Universities.
文摘We introduce Hair-GAN,an architecture of generative adversarial networks,to recover the 3D hair structure from a single image.The goal of our networks is to build a parametric transformation from 2D hair maps to 3D hair structure.The 3D hair structure is represented as a 3D volumetric field which encodes both the occupancy and the orientation information of the hair strands.Given a single hair image,we first align it with a bust model and extract a set of 2D maps encoding the hair orientation information in 2D,along with the bust depth map to feed into our Hair-GAN.With our generator network,we compute the 3D volumetric field as the structure guidance for the final hair synthesis.The modeling results not only resemble the hair in the input image but also possesses many vivid details in other views.The efficacy of our method is demonstrated by using a variety of hairstyles and comparing with the prior art.
基金supported by the National Natural Science Foundation of China(Grant No.11872080)Beijing Natural Science Foundation(Grant No.3192005).
文摘This paper presents a deep learning-based topology optimization method for the joint design of material layout and fiber orientation in continuous fiber-reinforced composite structure(CFRCS).The proposed method mainly includes three steps:(1)a ResUNet-involved generative and adversarial network(ResUNet-GAN)is developed to establish the end-to-end mapping from structural design parameters to fiber-reinforced composite optimized structure,and a fiber orientation chromatogram is presented to represent continuous fiber angles;(2)to avoid the local optimum problem,the independent continuous mapping method(ICM method)considering the improved principal stress orientation interpolated continuous fiber angle optimization(PSO-CFAO)strategy is utilized to construct CFRCS topology optimization dataset;(3)the well-trained ResUNet-GAN is deployed to design the optimal structural material distribution together with the corresponding continuous fiber orientations.Numerical simulations for benchmark structure verify that the proposed method greatly improves the design efficiency of CFRCS along with high design accuracy.Furthermore,the CFRCS topology configuration designed by ResUNet-GAN is fabricated by additive manufacturing.Compression experiments of the specimens show that both the stiffness structure and peak load of the CFRCS topology configuration designed by the proposed method have significantly enhanced.The proposed deep learning-based topology optimization method will provide great flexibility in CFRCS for engineering applications.
基金supported by the National Natural Science Foundation of China(Grant No.51978295)。
文摘In China,traditional village layouts are dynamic,harmoniously integrated with the natural environment,and rich in unique cultural characteristics.However,rapidly constructed villages often lack professional design,resulting in overly simple layouts and causing the villages to lose their traditional characteristics.Artiflcial intelligence holds the potential to alleviate this speciflc challenge.This study employs CGAN to generate comprehensive village layouts based on archetypal traditional villages,while also exploring parameters and network architectures to enhance result quality.The research address on traditional villages in southwestern Hubei,reflning generative factors,introducing image-based geographic scales,and employing machine vision to address data scarcity.The key flndings of this study includes:1)The research explores a class of AI-generated evaluation metrics suitable for village layout generation.2)It conflrms that the combination of the Unet_256 generator with the LSGAN architecture yields the best results in image generation.3)It is observed that the optimal generation results are achieved when the equivalent geographic scale of the image is 150 m×150 m.The study validates that GANs can be effectively applied in the village layout,producing layout results that incorporate traditional local experiences.This provides a novel approach to village layout.
基金supported in part by the Gusu Innovation and Entrepreneurship Leading Talents in Suzhou City,grant numbers ZXL2021425 and ZXL2022476Doctor of Innovation and Entrepreneurship Program in Jiangsu Province,grant number JSSCBS20211440+6 种基金Jiangsu Province Key R&D Program,grant number BE2019682Natural Science Foundation of Jiangsu Province,grant number BK20200214National Key R&D Program of China,grant number 2017YFB0403701National Natural Science Foundation of China,grant numbers 61605210,61675226,and 62075235Youth Innovation Promotion Association of Chinese Academy of Sciences,grant number 2019320Frontier Science Research Project of the Chinese Academy of Sciences,grant number QYZDB-SSW-JSC03Strategic Priority Research Program of the Chinese Academy of Sciences,grant number XDB02060000.
文摘The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.
基金This work was supported in part by the Basic Scientific Research Project of Liaoning Provincial Department of Education under Grant Nos.LJKQZ2021152 and LJ2020JCL007in part by the National Science Foundation of China(NSFC)under Grant No.61602226in part by the PhD Startup Foundation of Liaoning Technical University of China under Grant Nos.18-1021.
文摘To address the problems of lack of high-frequency information and texture details and unstable training in superresolution generative adversarial net-works,this paper optimizes the generator and discriminator based on the SRGAN model.First,the residual dense block is used as the basic structural unit of the gen-erator to improve the network’s feature extraction capability.Second,enhanced lightweight coordinate attention is incorporated to help the network more precisely concentrate on high-frequency location information,thereby allowing the gener-ator to produce more realistic image reconstruction results.Then,we propose a symmetric and efficient pyramidal segmentation attention discriminator network in which the attention mechanism is capable of derivingfiner-grained multiscale spatial information and creating long-term dependencies between multiscale chan-nel attentions,thus enhancing the discriminative ability of the network.Finally,a Charbonnier loss function and a gradient variance loss function with improved robustness are used to better realize the image’s texture structure and enhance the model’s stability.Thefindings from the experiments reveal that the reconstructed image quality enhances the average peak signal-to-noise ratio(PSNR)by 1.59 dB and the structural similarity index(SSIM)by 0.045 when compared to SRGAN on the three test sets.Compared with the state-of-the-art methods,the reconstructed images have a clearer texture structure,richer high-frequency details,and better visual effects.
基金supported by the National Natural Science Foundation of China(Grant Nos.52322305 and 52473098)the starting Grant of ShanghaiTech University,the Double First-Class Initiative Fund of ShanghaiTech University and the Shanghai Clinical Research and Trial Center.Materials were tested at the Analytical Instrumentation Center(Grant No.SPST-AIC10112914)the Center for High-resolution Electron Microscopy(C-hEM),SPST,ShanghaiTech University.
文摘2D patterned hollow structures have emerged as advanced materials with exceptional mechanical properties and lightweight characteristics,making them ideal for high-performance applications in aerospace and automotive industries.However,optimizing their structural design to achieve uniform stress distribution and minimize stress concentration remains a significant challenge due to the complex interplay between geometric patterns and mechanical performance.In this study,we develop an integrated framework combining conditional generative adversarial networks(cGANs)and deep Q-networks(DQNs)to predict and optimize the stress fields of 2D-PHS.We generated a comprehensive dataet comprising 1000 samples across five distinct density classes using a custom grid pattern generation algorithm,ensuring a wide range of structural variations.The cGAN accurately predicts stress distributions,achieving a high correlation with finite element analysis(FEA)results while reducing computational time from approximately 40 s(FEA)to just 1-2 s per prediction.Concurrently,the DQN optimizes design parameters through scaling and rotation operations,enhancing structural performance based on predicted stress metrics.Our approach resulted in a 4.3%improvement in average stress uniformity and a 23.1%reduction in maximum stress concentration.These improvements were validated through FEA simulations and experimental tensile tests on 3D-printed thermoplastic polyurethane samples.The tensile strength of the optimized samples increased from an initial average of 5.9-6.6 MPa under 100%strain,demonstrating enhanced mechanical resilience.This study demonstrates the efficacy of combining advanced AI techniques for rapid and precise material design optimization,providing a scalable and cost-effective solution for developing superior lightweight materials with tailored mechanical properties for critical engineering applications.
基金This work was supported by the National Key R&D Program of China(2018YFB1003404)the National Natural Science Foundation of China(Grant Nos.61872070,U1811261)+1 种基金the Fundamental Research Funds for the Central Universities(N171605001)Liao Ning Revitalization Talents Program(XLYC1807158).
文摘Network embedding which aims to embed a given network into a low-dimensional vector space has been proved effective in various network analysis and mining tasks such as node classification,link prediction and network visualization.The emerging network embedding methods have shifted of emphasis in utilizing mature deep learning models.The neural-network based network embedding has become a mainstream solution because of its high eficiency and capability of preserv-ing the nonlinear characteristics of the network.In this paper,we propose Adversarial Network Embedding using Structural Similarity(ANESS),a novel,versatile,low-complexity GAN-based network embedding model which utilizes the inherent vertex-to-vertex structural similarity attribute of the network.ANESS learns robustness and ffective vertex embeddings via a adversarial training procedure.Specifically,our method aims to exploit the strengths of generative adversarial networks in generating high-quality samples and utilize the structural similarity identity of vertexes to learn the latent representations of a network.Meanwhile,ANESS can dynamically update the strategy of generating samples during each training iteration.The extensive experiments have been conducted on the several benchmark network datasets,and empirical results demon-strate that ANESS significantly outperforms other state-of-theart network embedding methods.
