Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting
Traffic forecasting is an important task for transportation engineering as it helps authorities to plan and control traffic flow, detect congestion, and reduce environmental impact. Deep learning techniques have gained traction in handling such complex datasets, but require expertise in neural archi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/5/3/44 |
| _version_ | 1797579078920830976 |
|---|---|
| author | Daniel Klosa Christof Büskens |
| author_facet | Daniel Klosa Christof Büskens |
| author_sort | Daniel Klosa |
| collection | DOAJ |
| description | Traffic forecasting is an important task for transportation engineering as it helps authorities to plan and control traffic flow, detect congestion, and reduce environmental impact. Deep learning techniques have gained traction in handling such complex datasets, but require expertise in neural architecture engineering, often beyond the scope of traffic management decision-makers. Our study aims to address this challenge by using neural architecture search (NAS) methods. These methods, which simplify neural architecture engineering by discovering task-specific neural architectures, are only recently applied to traffic prediction. We specifically focus on the performance estimation of neural architectures, a computationally demanding sub-problem of NAS, that often hinders the real-world application of these methods. Extending prior work on evolutionary NAS (ENAS), our work evaluates the utility of zero-cost (ZC) proxies, recently emerged cost-effective evaluators of network architectures. These proxies operate without necessitating training, thereby circumventing the computational bottleneck, albeit at a slight cost to accuracy. Our findings indicate that, when integrated into the ENAS framework, ZC proxies can accelerate the search process by two orders of magnitude at a small cost of accuracy. These results establish the viability of ZC proxies as a practical solution to accelerate NAS methods while maintaining model accuracy. Our research contributes to the domain by showcasing how ZC proxies can enhance the accessibility and usability of NAS methods for traffic forecasting, despite potential limitations in neural architecture engineering expertise. This novel approach significantly aids in the efficient application of deep learning techniques in real-world traffic management scenarios. |
| first_indexed | 2024-03-10T22:31:51Z |
| format | Article |
| id | doaj.art-3ef3d69f50414438bb3b759715ee7731 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-10T22:31:51Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-3ef3d69f50414438bb3b759715ee77312023-11-19T11:41:38ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902023-07-015383084610.3390/make5030044Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic ForecastingDaniel Klosa0Christof Büskens1WG Optimization and Optimal Control, Center for Industrial Mathematics, University of Bremen, 28359 Bremen, GermanyWG Optimization and Optimal Control, Center for Industrial Mathematics, University of Bremen, 28359 Bremen, GermanyTraffic forecasting is an important task for transportation engineering as it helps authorities to plan and control traffic flow, detect congestion, and reduce environmental impact. Deep learning techniques have gained traction in handling such complex datasets, but require expertise in neural architecture engineering, often beyond the scope of traffic management decision-makers. Our study aims to address this challenge by using neural architecture search (NAS) methods. These methods, which simplify neural architecture engineering by discovering task-specific neural architectures, are only recently applied to traffic prediction. We specifically focus on the performance estimation of neural architectures, a computationally demanding sub-problem of NAS, that often hinders the real-world application of these methods. Extending prior work on evolutionary NAS (ENAS), our work evaluates the utility of zero-cost (ZC) proxies, recently emerged cost-effective evaluators of network architectures. These proxies operate without necessitating training, thereby circumventing the computational bottleneck, albeit at a slight cost to accuracy. Our findings indicate that, when integrated into the ENAS framework, ZC proxies can accelerate the search process by two orders of magnitude at a small cost of accuracy. These results establish the viability of ZC proxies as a practical solution to accelerate NAS methods while maintaining model accuracy. Our research contributes to the domain by showcasing how ZC proxies can enhance the accessibility and usability of NAS methods for traffic forecasting, despite potential limitations in neural architecture engineering expertise. This novel approach significantly aids in the efficient application of deep learning techniques in real-world traffic management scenarios.https://www.mdpi.com/2504-4990/5/3/44neural architecture searchtraffic forecastingzero-cost proxies |
| spellingShingle | Daniel Klosa Christof Büskens Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting Machine Learning and Knowledge Extraction neural architecture search traffic forecasting zero-cost proxies |
| title | Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting |
| title_full | Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting |
| title_fullStr | Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting |
| title_full_unstemmed | Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting |
| title_short | Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting |
| title_sort | low cost evolutionary neural architecture search lenas applied to traffic forecasting |
| topic | neural architecture search traffic forecasting zero-cost proxies |
| url | https://www.mdpi.com/2504-4990/5/3/44 |
| work_keys_str_mv | AT danielklosa lowcostevolutionaryneuralarchitecturesearchlenasappliedtotrafficforecasting AT christofbuskens lowcostevolutionaryneuralarchitecturesearchlenasappliedtotrafficforecasting |