NSTL国家科技图书文献中心

1. Knowledge-aware evolutionary graph neural architecture search NSTL国家科技图书文献中心

Wang C. | Zhao J.... - 《Knowledge-based systems》 - 2025,309(Jan.30) - 1.1～1.15 - 共15页

摘要：© 2024 Elsevier B.V.Graph neural architecture | search (GNAS) can customize high-performance graph | neural network architectures for specific graph tasks | , ignoring the prior knowledge that may improve the search | the multi-objective evolutionary search* on a new*

关键词： Evolutionary transfer optimization | Graph neural architecture search | Graph neural network

2. Efficient Self-Supervised Neural Architecture Search NSTL国家科技图书文献中心

Sri Aditya Deevi | Asish Kumar Mishra ... - 《2025 19th International Conference on Ubiquitous Information Management and Communication》 - International Conference on Ubiquitous Information Management and Communication - 2025, - 1～8 - 共8页

摘要： Neural Architecture Search (NAS) is a promising area to | Deep Neural* Networks (DNNs) have successfully* | expert practitioners' careful design of neural | memory to arrive at an optimal architecture. Automated | lengthy search* time, high processor needs, and a*

关键词： Accuracy | Memory management | Manuals | Inspection | Neural architecture search | Information management

3. Scalable reinforcement learning-based neural architecture search NSTL国家科技图书文献中心

Amber,Cassimon | Siegfried,Mercelis ... - 《Neural computing & applications》 - 2025,37(1) - 231～261 - 共31页

摘要： architecture search agent aimed at amortizing the initial | We assess the feasibility of a reusable neural | time-investment in building a good search* strategy* | best way to modify a given neural* network* | architecture. This is achieved using a transformer-based

关键词： Neural architecture search | AutoML | Deep learning | Reinforcement learning

4. Dependency-Aware Differentiable Neural Architecture Search NSTL国家科技图书文献中心

Buang Zhang | Xinle Wu ... - 《Computer Vision - ECCV 2024,Part LV》 - European Conference on Computer Vision - 2025, - 219～236 - 共18页

摘要：Neural architecture search (NAS) reduces the | neural network architectures, among which differential | for the search* efficiency. Despite achieving* | a high-performance architecture* distribution* | . Specifically, we model the architecture* distribution in DARTS*

关键词： Neural architecture search (NAS) | Differentiable NAS | Architecture distribution | Dependency-aware modeling

5. Network-aware federated neural architecture search NSTL国家科技图书文献中心

Goektug Ocal | Atay OEzgoevde - 《Future generations computer systems》 - 2025,162(Jan.) - 107475.1～107475.15 - 共15页

摘要：. Neural* Architecture Search (NAS) has emerged to* | automate the search for the best-performing neural | introduce Network-Aware Federated Neural Architecture | Search (NAFNAS), an open-source federated neural | . However, the success of DL relies on optimal Deep Neural

关键词： Neural architecture search | Federated learning | Network pruning | Client selection | Client grouping | Network emulation

6. Efficient Neural Architecture Search: Computational Cost Reduction Mechanisms in DeepGA NSTL国家科技图书文献中心

Jesus-Arnulfo Barrad... | Carlos-Alberto Lopez...... - 《Advances in Computational Intelligence. MICAI 2023 International Workshops,Part II》 - Mexican International Conference on Artificial Intelligence - 2025, - 125～134 - 共10页

摘要：Neural Architecture Search (NAS) aims to | automate the design process of Deep Neural* Networks (DNN* | architectures of Convolutional Neural* Networks (CNNs) for* | performance of the resulting architecture. The previous | ) without requiring profound domain knowledge. The Deep

关键词： Neural architecture search | Cost reduction | Convolutional neural networks

7. MCGRAN: Multi-conditional Graph Generation for Neural Architecture Search NSTL国家科技图书文献中心

Sathish Purushothama... | Julian Stier ... - 《Machine Learning,Optimization,and Data Science,Part I》 - International Conference on Machine Learning,Optimization,and Data Science - 2025, - 302～316 - 共15页

摘要： in Neural Architecture Search. MCGRAN learns neural | . With proper conditioning MCGRAN can generate neural | the generated neural* network architectures are novel* | and unique. Using an iterative conditional search | , we show that neural* network architectures can*

关键词： Graph generative models | Neural architecture search

8. Contrastive meta-reinforcement learning for heterogeneous graph neural architecture search NSTL国家科技图书文献中心

Zixuan Xu | Jia Wu - 《Expert Systems with Application》 - 2025,260(Jan.) - 125433.1～125433.13 - 共13页

摘要： Heterogeneous Graph Neural* Architecture Search (CM-HGNAS). Our* | Heterogeneous Graph Neural* Networks (HGNNs* | effective HGNN architecture* is a challenging task that* | . Fortunately, the advent of Heterogeneous Graph Architecture | Search (HGNAS) has automated this process and yielded

关键词： Heterogeneous graph neural architecture search | Meta-learning | Contrastive learning

9. Listwise ranking predictor for evolutionary neural architecture search NSTL国家科技图书文献中心

Li, Nan | Ma, Lianbo ... - 《Swarm and Evolutionary Computation》 - 2025,96 - 101956.1～101956.15 - 共15页

摘要：In evolutionary neural architecture search | directly predict the ranking of each architecture* instead* | architecture. Specifically, the training data is constructed | (ENAS), the accuracy predictors (i.e., regression | models) have been successfully applied to save

关键词： Neural architecture search | Listwise ranking predictor | Random encoding-combination

10. Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting NSTL国家科技图书文献中心

DONGHUI CHEN | LING CHEN ... - 《ACM transactions on knowledge discovery from data》 - 2025,19(1) - 11.1～11.23 - 共23页

摘要：-aware neural* architecture search framework for MTS* | learning, and neural* architecture search modules are* | any prior knowledge. For MTS forecasting, a search | Multivariate time series (MTS) forecasting has | attracted much attention in many intelligent applications

摘要：© 2024 Elsevier B.V.Graph neural architecture | search (GNAS) can customize high-performance graph | neural network architectures for specific graph tasks | , ignoring the prior knowledge that may improve the search | the multi-objective evolutionary search* on a new*

关键词： Evolutionary transfer optimization | Graph neural architecture search | Graph neural network

摘要： Neural Architecture Search (NAS) is a promising area to | Deep Neural* Networks (DNNs) have successfully* | expert practitioners' careful design of neural | memory to arrive at an optimal architecture. Automated | lengthy search* time, high processor needs, and a*

关键词： Accuracy | Memory management | Manuals | Inspection | Neural architecture search | Information management

摘要： architecture search agent aimed at amortizing the initial | We assess the feasibility of a reusable neural | time-investment in building a good search* strategy* | best way to modify a given neural* network* | architecture. This is achieved using a transformer-based

关键词： Neural architecture search | AutoML | Deep learning | Reinforcement learning

摘要：Neural architecture search (NAS) reduces the | neural network architectures, among which differential | for the search* efficiency. Despite achieving* | a high-performance architecture* distribution* | . Specifically, we model the architecture* distribution in DARTS*

关键词： Neural architecture search (NAS) | Differentiable NAS | Architecture distribution | Dependency-aware modeling

摘要：. Neural* Architecture Search (NAS) has emerged to* | automate the search for the best-performing neural | introduce Network-Aware Federated Neural Architecture | Search (NAFNAS), an open-source federated neural | . However, the success of DL relies on optimal Deep Neural

关键词： Neural architecture search | Federated learning | Network pruning | Client selection | Client grouping | Network emulation

摘要：Neural Architecture Search (NAS) aims to | automate the design process of Deep Neural* Networks (DNN* | architectures of Convolutional Neural* Networks (CNNs) for* | performance of the resulting architecture. The previous | ) without requiring profound domain knowledge. The Deep

关键词： Neural architecture search | Cost reduction | Convolutional neural networks

摘要： in Neural Architecture Search. MCGRAN learns neural | . With proper conditioning MCGRAN can generate neural | the generated neural* network architectures are novel* | and unique. Using an iterative conditional search | , we show that neural* network architectures can*

关键词： Graph generative models | Neural architecture search

摘要： Heterogeneous Graph Neural* Architecture Search (CM-HGNAS). Our* | Heterogeneous Graph Neural* Networks (HGNNs* | effective HGNN architecture* is a challenging task that* | . Fortunately, the advent of Heterogeneous Graph Architecture | Search (HGNAS) has automated this process and yielded

关键词： Heterogeneous graph neural architecture search | Meta-learning | Contrastive learning

摘要：In evolutionary neural architecture search | directly predict the ranking of each architecture* instead* | architecture. Specifically, the training data is constructed | (ENAS), the accuracy predictors (i.e., regression | models) have been successfully applied to save

关键词： Neural architecture search | Listwise ranking predictor | Random encoding-combination

摘要：-aware neural* architecture search framework for MTS* | learning, and neural* architecture search modules are* | any prior knowledge. For MTS forecasting, a search | Multivariate time series (MTS) forecasting has | attracted much attention in many intelligent applications

关键词： Multivariate time series forecasting | neural architecture search | graph learning | multi-scale decomposition

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：© 2024 Elsevier B.V.Graph neural architecture | search (GNAS) can customize high-performance graph | neural network architectures for specific graph tasks | , ignoring the prior knowledge that may improve the search | the multi-objective evolutionary search on a new

关键词： Evolutionary transfer optimization | Graph neural architecture search | Graph neural network

摘要： Neural Architecture Search (NAS) is a promising area to | Deep Neural Networks (DNNs) have successfully | expert practitioners' careful design of neural | memory to arrive at an optimal architecture. Automated | lengthy search time, high processor needs, and a

关键词： Accuracy | Memory management | Manuals | Inspection | Neural architecture search | Information management

摘要： architecture search agent aimed at amortizing the initial | We assess the feasibility of a reusable neural | time-investment in building a good search strategy | best way to modify a given neural network | architecture. This is achieved using a transformer-based

关键词： Neural architecture search | AutoML | Deep learning | Reinforcement learning

摘要：Neural architecture search (NAS) reduces the | neural network architectures, among which differential | for the search efficiency. Despite achieving | a high-performance architecture distribution | . Specifically, we model the architecture distribution in DARTS

关键词： Neural architecture search (NAS) | Differentiable NAS | Architecture distribution | Dependency-aware modeling

摘要：. Neural Architecture Search (NAS) has emerged to | automate the search for the best-performing neural | introduce Network-Aware Federated Neural Architecture | Search (NAFNAS), an open-source federated neural | . However, the success of DL relies on optimal Deep Neural

关键词： Neural architecture search | Federated learning | Network pruning | Client selection | Client grouping | Network emulation

摘要：Neural Architecture Search (NAS) aims to | automate the design process of Deep Neural Networks (DNN | architectures of Convolutional Neural Networks (CNNs) for | performance of the resulting architecture. The previous | ) without requiring profound domain knowledge. The Deep

关键词： Neural architecture search | Cost reduction | Convolutional neural networks

摘要： in Neural Architecture Search. MCGRAN learns neural | . With proper conditioning MCGRAN can generate neural | the generated neural network architectures are novel | and unique. Using an iterative conditional search | , we show that neural network architectures can

关键词： Graph generative models | Neural architecture search

摘要： Heterogeneous Graph Neural Architecture Search (CM-HGNAS). Our | Heterogeneous Graph Neural Networks (HGNNs | effective HGNN architecture is a challenging task that | . Fortunately, the advent of Heterogeneous Graph Architecture | Search (HGNAS) has automated this process and yielded

关键词： Heterogeneous graph neural architecture search | Meta-learning | Contrastive learning

摘要：In evolutionary neural architecture search | directly predict the ranking of each architecture instead | architecture. Specifically, the training data is constructed | (ENAS), the accuracy predictors (i.e., regression | models) have been successfully applied to save

关键词： Neural architecture search | Listwise ranking predictor | Random encoding-combination

摘要：-aware neural architecture search framework for MTS | learning, and neural architecture search modules are | any prior knowledge. For MTS forecasting, a search | Multivariate time series (MTS) forecasting has | attracted much attention in many intelligent applications

关键词： Multivariate time series forecasting | neural architecture search | graph learning | multi-scale decomposition

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：© 2024 Elsevier B.V.Graph neural architecture | search (GNAS) can customize high-performance graph | neural network architectures for specific graph tasks | , ignoring the prior knowledge that may improve the search | the multi-objective evolutionary search* on a new*

摘要： Neural Architecture Search (NAS) is a promising area to | Deep Neural* Networks (DNNs) have successfully* | expert practitioners' careful design of neural | memory to arrive at an optimal architecture. Automated | lengthy search* time, high processor needs, and a*

摘要： architecture search agent aimed at amortizing the initial | We assess the feasibility of a reusable neural | time-investment in building a good search* strategy* | best way to modify a given neural* network* | architecture. This is achieved using a transformer-based

摘要：Neural architecture search (NAS) reduces the | neural network architectures, among which differential | for the search* efficiency. Despite achieving* | a high-performance architecture* distribution* | . Specifically, we model the architecture* distribution in DARTS*

摘要：. Neural* Architecture Search (NAS) has emerged to* | automate the search for the best-performing neural | introduce Network-Aware Federated Neural Architecture | Search (NAFNAS), an open-source federated neural | . However, the success of DL relies on optimal Deep Neural

摘要：Neural Architecture Search (NAS) aims to | automate the design process of Deep Neural* Networks (DNN* | architectures of Convolutional Neural* Networks (CNNs) for* | performance of the resulting architecture. The previous | ) without requiring profound domain knowledge. The Deep

摘要： in Neural Architecture Search. MCGRAN learns neural | . With proper conditioning MCGRAN can generate neural | the generated neural* network architectures are novel* | and unique. Using an iterative conditional search | , we show that neural* network architectures can*

摘要：In evolutionary neural architecture search | directly predict the ranking of each architecture* instead* | architecture. Specifically, the training data is constructed | (ENAS), the accuracy predictors (i.e., regression | models) have been successfully applied to save

摘要：-aware neural* architecture search framework for MTS* | learning, and neural* architecture search modules are* | any prior knowledge. For MTS forecasting, a search | Multivariate time series (MTS) forecasting has | attracted much attention in many intelligent applications