相关论文: K-shot NAS: Learnable Weight-Sharing for NAS with …

Gradient-based one-shot neural architecture search (NAS) has significantly reduced the cost of exploring architectural spaces with discrete design choices, such as selecting operations within a model. However, the field faces two major…

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is…

In this paper, we propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search. Differentiable architecture search (DARTS) acquires the optimal architectures by optimizing the…

Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We…

Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we…

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…

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

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…

Multi-task neural architecture search (NAS) enables transferring architectural knowledge among different tasks. However, ranking disorder between the source task and the target task degrades the architecture performance on the downstream…

Multi-task learning (MTL) aims to make full use of the knowledge contained in multi-task supervision signals to improve the overall performance. How to make the knowledge of multiple tasks shared appropriately is an open problem for MTL.…

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art…

Benefiting from the search efficiency, differentiable neural architecture search (NAS) has evolved as the most dominant alternative to automatically design competitive deep neural networks (DNNs). We note that DNNs must be executed under…

Automatic neural architecture search techniques are becoming increasingly important in machine learning area. Especially, weight sharing methods have shown remarkable potentials on searching good network architectures with few computational…

Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only few hours? NAS methods automate the design of Convolutional Networks (ConvNets) under hardware constraints and they have emerged as key components of…

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge…

Convolutional neural networks (CNNs) are vulnerable to adversarial examples, and studies show that increasing the model capacity of an architecture topology (e.g., width expansion) can bring consistent robustness improvements. This reveals…

The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs). However, the weights sampling strategy of WSNet…

Efficient hyperparameter or architecture search methods have shown remarkable results, but each of them is only applicable to searching for either hyperparameters (HPs) or architectures. In this work, we propose a unified pipeline, AutoHAS,…

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate…