paper-with-me

홈 › Papers

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

2020-12-01 · NeurIPS 2020 12 · Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, ZongYuan Ge, Steven Su

Recent works on One-Shot Neural Architecture Search (NAS) mostly adopt a bilevel optimization scheme to alternatively optimize the supernet weights and architecture parameters after relaxing the discrete search space into a differentiable space. However, the non-negligible incongruence in their relaxation methods is hard to guarantee the differentiable optimization in the continuous space is equivalent to the optimization in the discrete space. Differently, this paper utilizes a variational graph autoencoder to injectively transform the discrete architecture space into an equivalently continuous latent space, to resolve the incongruence. A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search. As the catastrophic forgetting in differentiable One-Shot NAS deteriorates supernet predictive ability and makes the bilevel optimization inefficient, this paper further proposes an architecture complementation method to relieve this deficiency. We analyze the effectiveness of the proposed method, and a series of experiments have been conducted to compare the proposed method with state-of-the-art One-Shot NAS methods.

📄 PDF Abstract BibTeX

Code (1)

MiaoZhang0525/EENAS pytorch

Tasks

Bilevel OptimizationNeural Architecture Search

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration

2023-01-23 · Deokki Hong, Kanghyun Choi, Hye Yoon Lee, Joonsang Yu 외

Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems. The large co-exploration …

Neural Architecture Search

ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators

2021-09-29 · Deokki Hong, Kanghyun Choi, Hey Yoon Lee, Joonsang Yu 외

While DNNs achieve over-human performances in a number of areas, it is often accompanied by the skyrocketing computational costs. Co-exploration of an optimal neural architecture and its hardware accelerator is an appro…

Neural Architecture Search

Flexible Channel Dimensions for Differentiable Architecture Search

2023-06-13 · Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

Finding optimal channel dimensions (i.e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints. Recent work in neural architecture search aims at aut…

GPUNeural Architecture Search

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search

2021-01-27 · CVPR 2021 1 · Yibo Yang, Shan You, Hongyang Li, Fei Wang 외

Most differentiable neural architecture search methods construct a super-net for search and derive a target-net as its sub-graph for evaluation. There exists a significant gap between the architectures in search and eval…

GPUNeural Architecture Search

AutoSpace: Neural Architecture Search with Less Human Interference

2021-03-22 · ICCV 2021 10 · Daquan Zhou, Xiaojie Jin, Xiaochen Lian, Linjie Yang 외

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize h…

Neural Architecture Search