相关论文: Stronger NAS with Weaker Predictors

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

Neural architecture search (NAS) is an approach for automatically designing a neural network architecture without human effort or expert knowledge. However, the high computational cost of NAS limits its use in commercial applications. Two…

Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures. Differentiable neural architecture search (DARTS) is a promising NAS approach that dramatically increases search efficiency.…

Zero-cost proxies are nowadays frequently studied and used to search for neural architectures. They show an impressive ability to predict the performance of architectures by making use of their untrained weights. These techniques allow for…

Neural architecture search (NAS) with an accuracy predictor that predicts the accuracy of candidate architectures has drawn increasing attention due to its simplicity and effectiveness. Previous works usually employ neural network-based…

Practical use of neural networks often involves requirements on latency, energy and memory among others. A popular approach to find networks under such requirements is through constrained Neural Architecture Search (NAS). However, previous…

Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. In this paper, we propose Generative Adversarial NAS (GA-NAS)…

Neural Architecture Search (NAS), the process of automating architecture engineering, is an appealing next step to advancing end-to-end Automatic Speech Recognition (ASR), replacing expert-designed networks with learned, task-specific…

Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS). Although very appealing, this framework is not without…

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be…

Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim at finding architectures that optimize the prediction…

Search spaces hallmark the advancement of Neural Architecture Search (NAS). Large and complex search spaces with versatile building operators and structures provide more opportunities to brew promising architectures, yet pose severe…

Neural architecture search (NAS) has attracted a lot of attention and has been illustrated to bring tangible benefits in a large number of applications in the past few years. Architecture topology and architecture size have been regarded as…

Deep learning models have proven to be successful in a wide range of machine learning tasks. Yet, they are often highly sensitive to perturbations on the input data which can lead to incorrect decisions with high confidence, hampering their…

Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can…

Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures,…

Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the…

Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. Despite these high expectation, the effectiveness and…

Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of…

Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-shot NAS approaches is to design proxies that can predict…