Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications
Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analyses on the same data) and are deployed on resour...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11091315/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246186015293440 |
|---|---|
| author | Md Hafizur Rahman Zafaryab Haider Md Mashfiq Rizvee Sumaiya Shomaji Prabuddha Chakraborty |
| author_facet | Md Hafizur Rahman Zafaryab Haider Md Mashfiq Rizvee Sumaiya Shomaji Prabuddha Chakraborty |
| author_sort | Md Hafizur Rahman |
| collection | DOAJ |
| description | Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analyses on the same data) and are deployed on resource-constrained edge devices, requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, we propose a new paradigm of intelligent neural network architecture search framework (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. ILASH utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and frames per second (FPS). We perform extensive evaluations of the proposed layer shared architecture paradigm and the ILASH framework using three open-source datasets (UTKFace, MTFL, and CelebA). We compare ILASH with two different neural architecture search libraries that support multi-task applications (LibMTL and AutoKeras). We also evaluate ILASH against two standard neural architecture search frameworks (DARTS and ENAS). ILASH was able to surpass state-of-the-art performance across most comparison metrics (e.g. task accuracy, search/inference energy, and fps). |
| format | Article |
| id | doaj-art-a638749eed7c4e6483d4aa9346ddcf5f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a638749eed7c4e6483d4aa9346ddcf5f2025-08-20T03:58:35ZengIEEEIEEE Access2169-35362025-01-011313276713278110.1109/ACCESS.2025.359203911091315Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task ApplicationsMd Hafizur Rahman0https://orcid.org/0000-0002-1981-6582Zafaryab Haider1https://orcid.org/0000-0003-1849-5817Md Mashfiq Rizvee2https://orcid.org/0000-0001-7414-7951Sumaiya Shomaji3Prabuddha Chakraborty4https://orcid.org/0000-0002-5102-4200Department of Electrical and Computer Engineering, University of Maine, Orono, ME, USADepartment of Electrical and Computer Engineering, University of Maine, Orono, ME, USADepartment of Electrical Engineering and Computer Science, University of Kansas, Lawrence, KS, USADepartment of Electrical Engineering and Computer Science, University of Kansas, Lawrence, KS, USADepartment of Electrical and Computer Engineering, University of Maine, Orono, ME, USAArtificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analyses on the same data) and are deployed on resource-constrained edge devices, requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, we propose a new paradigm of intelligent neural network architecture search framework (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. ILASH utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and frames per second (FPS). We perform extensive evaluations of the proposed layer shared architecture paradigm and the ILASH framework using three open-source datasets (UTKFace, MTFL, and CelebA). We compare ILASH with two different neural architecture search libraries that support multi-task applications (LibMTL and AutoKeras). We also evaluate ILASH against two standard neural architecture search frameworks (DARTS and ENAS). ILASH was able to surpass state-of-the-art performance across most comparison metrics (e.g. task accuracy, search/inference energy, and fps).https://ieeexplore.ieee.org/document/11091315/Deep learningmultitask learningneural architecture search (NAS) |
| spellingShingle | Md Hafizur Rahman Zafaryab Haider Md Mashfiq Rizvee Sumaiya Shomaji Prabuddha Chakraborty Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications IEEE Access Deep learning multitask learning neural architecture search (NAS) |
| title | Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications |
| title_full | Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications |
| title_fullStr | Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications |
| title_full_unstemmed | Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications |
| title_short | Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications |
| title_sort | intelligent layer sharing ilash a predictive neural architecture search framework for multi task applications |
| topic | Deep learning multitask learning neural architecture search (NAS) |
| url | https://ieeexplore.ieee.org/document/11091315/ |
| work_keys_str_mv | AT mdhafizurrahman intelligentlayersharingilashapredictiveneuralarchitecturesearchframeworkformultitaskapplications AT zafaryabhaider intelligentlayersharingilashapredictiveneuralarchitecturesearchframeworkformultitaskapplications AT mdmashfiqrizvee intelligentlayersharingilashapredictiveneuralarchitecturesearchframeworkformultitaskapplications AT sumaiyashomaji intelligentlayersharingilashapredictiveneuralarchitecturesearchframeworkformultitaskapplications AT prabuddhachakraborty intelligentlayersharingilashapredictiveneuralarchitecturesearchframeworkformultitaskapplications |