Weight-sharing neural architecture search: A battle to shrink the optimization gap

L Xie, X Chen, K Bi, L Wei, Y Xu, L Wang… - ACM Computing …, 2021 - dl.acm.org
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

[HTML][HTML] Neural architecture search: A contemporary literature review for computer vision applications

M Poyser, TP Breckon - Pattern Recognition, 2024 - Elsevier
Abstract Deep Neural Networks have received considerable attention in recent years. As the
complexity of network architecture increases in relation to the task complexity, it becomes …

Ista-nas: Efficient and consistent neural architecture search by sparse coding

Y Yang, H Li, S You, F Wang… - Advances in Neural …, 2020 - proceedings.neurips.cc
Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-
dimensional space spanned by all candidate connections. Current gradient-based NAS …

Sphynx: A deep neural network design for private inference

M Cho, Z Ghodsi, B Reagen, S Garg… - IEEE Security & …, 2022 - ieeexplore.ieee.org
Sphynx: A Deep Neural Network Design for Private Inference Page 1 22 September/October
2022 Copublished by the IEEE Computer and Reliability Societies 1540-7993/22©2022IEEE …

Single-path mobile automl: Efficient convnet design and nas hyperparameter optimization

D Stamoulis, R Ding, D Wang… - IEEE Journal of …, 2020 - ieeexplore.ieee.org
Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only
a few hours? NAS methods automate the design of Convolutional Networks (ConvNets) …

Progressive feature interaction search for deep sparse network

C Gao, Y Li, Q Yao, D Jin, Y Li - Advances in Neural …, 2021 - proceedings.neurips.cc
Deep sparse networks (DSNs), of which the crux is exploring the high-order feature
interactions, have become the state-of-the-art on the prediction task with high-sparsity …

Neural architecture search as sparse supernet

Y Wu, A Liu, Z Huang, S Zhang… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-
Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the …

Neural-architecture-search-based multiobjective cognitive automation system

EK Wang, SP Xu, CM Chen, N Kumar - IEEE Systems Journal, 2020 - ieeexplore.ieee.org
Currently, deep-learning-based cognitive automation for decision-making in industrial
informatics is a new hot topic in the field of cognitive computing, among which multiobjective …

Fisher task distance and its application in neural architecture search

CP Le, M Soltani, J Dong, V Tarokh - IEEE Access, 2022 - ieeexplore.ieee.org
We formulate an asymmetric (or non-commutative) distance between tasks based on Fisher
Information Matrices, called Fisher task distance. This distance represents the complexity of …

Task-aware neural architecture search

CP Le, M Soltani, R Ravier… - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
The design of handcrafted neural networks requires a lot of time and resources. Recent
techniques in Neural Architecture Search (NAS) have proven to be competitive or better than …