{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:25:22Z","timestamp":1766298322526},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:p>Neural Architecture Search (NAS) aims to automatically excavate the optimal network architecture with superior test performance. Recent neural architecture search (NAS) approaches rely on validation loss or accuracy to find the superior network for the target data. In this paper, we investigate a new neural architecture search measure for excavating architectures with better generalization. We demonstrate that the flatness of the loss surface can be a promising proxy for predicting the generalization capability of neural network architectures. We evaluate our proposed method on various search spaces, showing similar or even better performance compared to the state-of-the-art NAS methods. Notably, the resultant architecture found by flatness measure generalizes robustly to various shifts in data distribution (e.g. ImageNet-V2,-A,-O), as well as various tasks such as object detection and semantic segmentation.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/101","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"911-919","source":"Crossref","is-referenced-by-count":4,"title":["GeNAS: Neural Architecture Search with Better Generalization"],"prefix":"10.24963","author":[{"given":"Joonhyun","family":"Jeong","sequence":"first","affiliation":[{"name":"NAVER Cloud, Image Vision"},{"name":"Korea Advanced Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joonsang","family":"Yu","sequence":"additional","affiliation":[{"name":"NAVER Cloud, Image Vision"},{"name":"NAVER AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geondo","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyoon","family":"Han","sequence":"additional","affiliation":[{"name":"NAVER AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YoungJoon","family":"Yoo","sequence":"additional","affiliation":[{"name":"NAVER Cloud, Image Vision"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2023","name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","start":{"date-parts":[[2023,8,19]]},"theme":"Artificial Intelligence","location":"Macau, SAR China","end":{"date-parts":[[2023,8,25]]}},"container-title":["Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:35:23Z","timestamp":1691742923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/101"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2023\/101","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}