{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T23:35:07Z","timestamp":1762040107593,"version":"build-2065373602"},"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":[[2021,8]]},"abstract":"<jats:p>Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess.  In this paper, we propose Generative Adversarial NAS (GA-NAS) with theoretically provable convergence guarantees, promoting stability and reproducibility in neural architecture search. Inspired by importance sampling, GA-NAS iteratively fits a generator to previously discovered top architectures, thus increasingly focusing on important parts of a large search space. Furthermore, we propose an efficient adversarial learning approach, where the generator is trained by reinforcement learning based on rewards provided by a discriminator, thus being able to explore the search space without evaluating a large number of architectures. Extensive experiments show that GA-NAS beats the best published results under several cases on three public NAS benchmarks. In the meantime, GA-NAS can handle ad-hoc search constraints and search spaces. We show that GA-NAS can be used to improve already optimized baselines found by other NAS methods, including EfficientNet and ProxylessNAS, in terms of ImageNet accuracy or the number of parameters, in their original search space.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/307","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"2227-2234","source":"Crossref","is-referenced-by-count":2,"title":["Generative Adversarial Neural Architecture Search"],"prefix":"10.24963","author":[{"given":"Seyed Saeed","family":"Changiz Rezaei","sequence":"first","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}]},{"given":"Fred X.","family":"Han","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}]},{"given":"Di","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Alberta"}]},{"given":"Mohammad","family":"Salameh","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}]},{"given":"Keith","family":"Mills","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Alberta"}]},{"given":"Shuo","family":"Lian","sequence":"additional","affiliation":[{"name":"Huawei Kirin Solution, Shanghai, China"}]},{"given":"Wei","family":"Lu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}]},{"given":"Shangling","family":"Jui","sequence":"additional","affiliation":[{"name":"Huawei Kirin Solution, Shanghai, China"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:02:33Z","timestamp":1628679753000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.ijcai.org\/proceedings\/2021\/307"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.24963\/ijcai.2021\/307","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}