BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

Xiangning, Xie,; Liu, Yuqiao; Sun, Yanan; Yen, Gary G.; Xue, Bing; Zhang, Mengjie

doi:10.1109/tevc.2022.3147526

Cited by 15 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The batch size was set to 16 and the model was trained for 200 epochs. MultiStepLR is a learning rate decay method used in PyTorch [86] that adjusts the learning rate at set intervals [87]. The initial learning rate was set to 0.01.…”

Section: Training Methodsmentioning

confidence: 99%

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Tang,

Zhao,

Zhang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Abstract-Poverty is a global challenge, the effects of which are felt on the individual to national scale. To develop effective support policies to reduce poverty, local governments require precise poverty distribution data, which are lacking for many areas. In this study, we proposed a model to estimate poverty on a spatial scale of 10 × 10 km by combining features extracted from multiple data sources, including nighttime light remote sensing data, normalized difference vegetation index, surface reflectance, land cover type, and slope data, and applied the model to Nigeria. Considering that the trends of environmental factors contain valid information related to poverty, time-series features were extracted through convolutional long short-term memory and used for the assessment. The poverty level is represented by the wealth index derived from the Demographic and Health Survey Program. The model exhibited a good ability to estimate poverty, with an R 2 of 0.73 between the actual and estimated wealth index in Nigeria in 2018. Applying the proposed model to poverty estimation for Nigeria in 2021 yielded an R 2 value of 0.69, indicating good generalization ability. To further validate model reliability, we compared the assessment results with high-resolution satellite imagery and a state-level multidimensional poverty index. We also investigated the impact of incorporating time-series features on the accuracy of poverty assessment. Results showed that the addition of time-series features increased the accuracy of poverty estimation from 0.64 to 0.73. The proposed method has valuable applications for estimating poverty at the grid scale in countries without such data.

show abstract

Section: Training Methodsmentioning

confidence: 99%

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Tang,

Zhao,

Zhang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The evaluation of each individual in the algorithm is independent, so the population-based optimization algorithm easily performs parallel computing. Based on this feature, Xie et al [56] built the BenchENAS platform. When evaluating individual fitness, individuals in the population can be evaluated parallelly in a common lab environment, which significantly speeds up population evaluation and promotes the development of ENAS.…”

Section: Introductionmentioning

confidence: 99%

TPENAS: A Two-Phase Evolutionary Neural Architecture Search for Remote Sensing Image Classification

Feng

Sheng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The application of deep learning in remote sensing image classification has been paid more and more attention by industry and academia. However, manually designed remote sensing image classification models based on convolutional neural networks usually require sophisticated expert knowledge. Moreover, it is notoriously difficult to design a model with both high classification accuracy and few parameters. Recently, neural architecture search (NAS) has emerged as an effective method that can greatly reduce the heavy burden of manually designing models. However, it remains a challenge to search for a classification model with high classification accuracy and few parameters in the huge search space. To tackle this challenge, we propose TPENAS, a two-phase evolutionary neural architecture search framework, which optimizes the model using computational intelligence techniques in two search phases. In the first search phase, TPENAS searches for the optimal depth of the model. In the second search phase, TPENAS searches for the structure of the model from the perspective of the whole model. Experiments on three open benchmark datasets demonstrate that our proposed TPENAS outperforms the state-of-the-art baselines in both classification accuracy and reducing parameters.

show abstract

“…Even more, the RegularizedEvo algorithm [9] ran on 450 GPUs for 7 days. In practice, buying or renting such scales of GPU resources is commonly unaffordable for most researchers [19]. As a result, how to accelerate the TEM to reduce the prohibitive computational overhead is essential, which results in the research topic of EEMs in the NAS community [11].…”

Section: Introductionmentioning

confidence: 99%

Efficient Evaluation Methods for Neural Architecture Search: A Survey

Xie¹,

Song²,

Lv³

et al. 2023

Preprint

View full text Add to dashboard Cite

Neural Architecture Search (NAS) has received increasing attention because of its exceptional merits in automating the design of Deep Neural Network (DNN) architectures. However, the performance evaluation process, as a key part of NAS, often requires training a large number of DNNs. This inevitably causes NAS computationally expensive. In past years, many Efficient Evaluation Methods (EEMs) have been proposed to address this critical issue. In this paper, we comprehensively survey these EEMs published up to date, and provide a detailed analysis to motivate the further development of this research direction. Specifically, we divide the existing EEMs into four categories based on the number of DNNs trained for constructing these EEMs. The categorization can reflect the degree of efficiency in principle, which can in turn help quickly grasp the methodological features. In surveying each category, we further discuss the design principles and analyze the strength and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs. Furthermore, we also discuss the current challenges and issues to identify future research directions in this emerging topic. To the best of our knowledge, this is the first work that extensively and systematically surveys the EEMs of NAS.

show abstract

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

Cited by 15 publications

References 36 publications

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

TPENAS: A Two-Phase Evolutionary Neural Architecture Search for Remote Sensing Image Classification

Efficient Evaluation Methods for Neural Architecture Search: A Survey

Contact Info

Product

Resources

About