Mitigating Search Interference with Task-Aware Nested Search
- Authors
- Lee, Jiho; Kim, Eunwoo
- Issue Date
- 2024
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- multi-task learning; Neural architecture search; search interference
- Citation
- IEEE Transactions on Image Processing, v.33, pp 3102 - 3114
- Pages
- 13
- Journal Title
- IEEE Transactions on Image Processing
- Volume
- 33
- Start Page
- 3102
- End Page
- 3114
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73794
- DOI
- 10.1109/TIP.2024.3390996
- ISSN
- 1057-7149
1941-0042
- Abstract
- Neural Architecture Search (NAS) has emerged as a promising tool in the field of AutoML for designing more accurate and efficient architectures. The majority of NAS works employ a weight-sharing technique to reduce the search cost by sharing the weights of a supernet, which is a composite of all architectures produced from the search space. Nonetheless, this method has a significant drawback in that negative interference may arise when candidate architectures share the same weights. This issue becomes even more severe in multi-task searches, where a supernet is shared across tasks. To address this problem, we propose a task-aware nested search for multiple tasks that generates task-specific search spaces and architectures using a search-in-search approach consisting of space-search and architecture-search phases. In the space-search phase, we discover an optimal subspace in a task-aware manner by utilizing the proposed search space generator based on the global search space. On top of each subspace, we search for a promising architecture in the architecture-search phase. This method can mitigate search interference by adaptively sharing weights of the supernet by the generated subspace. The experimental results on various vision benchmarks (CityScapes, NYUv2, and Tiny-Taskonomy) show that the proposed method achieves outstanding performance over existing methods in terms of task accuracy, model parameters, and latency. IEEE
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73794)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.