相关论文: Pretraining Neural Architecture Search Controllers…

Data-driven, automatic design space exploration of neural accelerator architecture is desirable for specialization and productivity. Previous frameworks focus on sizing the numerical architectural hyper-parameters while neglect searching…

Reliable yet efficient evaluation of generalisation performance of a proposed architecture is crucial to the success of neural architecture search (NAS). Traditional approaches face a variety of limitations: training each architecture to…

Many hardware-aware neural architecture search (NAS) methods have been developed to optimize the topology of neural networks (NN) with the joint objectives of higher accuracy and lower latency. Recently, both accuracy and latency predictors…

Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by…

Neural Architecture Search (NAS) automates the design of high-performing neural networks but typically targets a single predefined task, thereby restricting its real-world applicability. To address this, Meta Neural Architecture Search…

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image…

Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the…

Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks. Unfortunately, the computational cost can make it difficult to scale. In this paper, we make the first attempt to…

Recently proposed neural architecture search (NAS) methods co-train billions of architectures in a supernet and estimate their potential accuracy using the network weights detached from the supernet. However, the ranking correlation between…

Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios. To obtain optimal data-specific GNN architectures, researchers turn to neural architecture search (NAS) methods, which have made impressive…

Recent neural architecture search (NAS) works proposed training-free metrics to rank networks which largely reduced the search cost in NAS. In this paper, we revisit these training-free metrics and find that: (1) the number of parameters…

Graph neural networks (GNN) has been successfully applied to operate on the graph-structured data. Given a specific scenario, rich human expertise and tremendous laborious trials are usually required to identify a suitable GNN architecture.…

Weight sharing, as an approach to speed up architecture performance estimation has received wide attention. Instead of training each architecture separately, weight sharing builds a supernet that assembles all the architectures as its…

A myriad of recent breakthroughs in hand-crafted neural architectures for visual recognition have highlighted the urgent need to explore hybrid architectures consisting of diversified building blocks. Meanwhile, neural architecture search…

Spatial-temporal sequence forecasting (STSF) is a long-standing research problem with widespread real-world applications. Neural architecture search (NAS), which automates the neural network design, has been shown effective in tackling the…

One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once. However, current methods select each operation independently…

Recent years have witnessed the popularity and success of graph neural networks (GNN) in various scenarios. To obtain data-specific GNN architectures, researchers turn to neural architecture search (NAS), which has made impressive success…

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the…

The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the…

Neural architecture search (NAS) automatically finds the best task-specific neural network topology, outperforming many manual architecture designs. However, it can be prohibitively expensive as the search requires training thousands of…