MDARTS: Multi-objective Differentiable Neural Architecture Search
- Title
- MDARTS: Multi-objective Differentiable Neural Architecture Search
- Authors
- 김성훈
- Date Issued
- 2020
- Publisher
- 포항공과대학교
- Abstract
- In this thesis, we present a differentiable neural architecture search (NAS)
method that takes into account two competing objectives, quality of result (QoR)
and quality of service (QoS) with hardware design constraints. NAS research has
recently received a lot of attention due to its ability to automatically find architecture
candidates that can outperform handcrafted ones. However, the NAS
approach which complies with actual HW design constraints has been underexplored.
A naive NAS approach for this would be to optimize a combination of
two criteria of QoR and QoS, but we first identify that the simple extension of the
prior art often yields degenerated architectures, and suffers from a sensitive hyperparameter
tuning. Instead, we propose to formulate it as a differentiable multiobjective
optimization, called MDARTS. MDARTS has an affordable search time
and can find Pareto front. We also identify the problematic gap between all the
existing differentiable NAS results and those final post-processed architectures, where soft connections are binarized. This gap leads to performance degradation
when being deployed. To mitigate this gap, we propose a separation loss that discourages
indefinite connections of components by implicitly minimizing entropy.
In our experiment, we show that MDARTS is able to find the architectures that
have lower error than the state-of-the-art (2.35 % and 14.99 % of top-1 test error
on CIFAR-10 and CIFAR-100, respectively) with an affordable latency for
hardware. Also, we found several architecture candidates that place even closer
to Pareto front than the ones obtained from the state-of-the-art NAS methods.
We also demonstrate MDARTS can complete a single search process within eight
GPU-hours on both CIFAR-10 and CIFAR-100.
- URI
- http://postech.dcollection.net/common/orgView/200000332828
https://oasis.postech.ac.kr/handle/2014.oak/111135
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.