Related papers: How to 0wn NAS in Your Spare Time

The term Neural Architecture Search (NAS) refers to the automatic optimization of network architectures for a new, previously unknown task. Since testing an architecture is computationally very expensive, many optimizers need days or even…

Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and require manual…

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…

Recently Neural Architecture Search (NAS) has aroused great interest in both academia and industry, however it remains challenging because of its huge and non-continuous search space. Instead of applying evolutionary algorithm or…

Semantic segmentation of 3D medical images is a challenging task due to the high variability of the shape and pattern of objects (such as organs or tumors). Given the recent success of deep learning in medical image segmentation, Neural…

Intrusion detection into computer networks has become one of the most important issues in cybersecurity. Attackers keep on researching and coding to discover new vulnerabilities to penetrate information security system. In consequence…

Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell…

Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this…

The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods. These methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization,…

Machine learning based malware detection techniques rely on grayscale images of malware and tends to classify malware based on the distribution of textures in graycale images. Albeit the advancement and promising results shown by machine…

To preserve user privacy while enabling mobile intelligence, techniques have been proposed to train deep neural networks on decentralized data. However, training over decentralized data makes the design of neural architecture quite…

Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training often has to run on-premise under strict data-local…

Adversarial robustness of deep learning models has gained much traction in the last few years. Various attacks and defenses are proposed to improve the adversarial robustness of modern-day deep learning architectures. While all these…

Reverse engineering deep ReLU networks is a critical problem in understanding the complex behavior and interpretability of neural networks. In this research, we present a novel method for reconstructing deep ReLU networks by leveraging…

Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious…

We study the robustness of data-centric methods to find neural network architectures, known as neural architecture search (NAS), against data poisoning. To audit this robustness, we design a poisoning framework that enables the systematic…

In the field of complex action recognition in videos, the quality of the designed model plays a crucial role in the final performance. However, artificially designed network structures often rely heavily on the researchers' knowledge and…

MLaaS Service Providers (SPs) holding a Neural Network would like to keep the Neural Network weights secret. On the other hand, users wish to utilize the SPs' Neural Network for inference without revealing their data. Multi-Party…

Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results. However, their success is based on vast computational resources (e.g. hundreds…

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing…