{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-objective-neural-architecture-search-1","title":"Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS","arxiv_id":"1911.09336","date":"2019-11-21","proceeding":"NeurIPS 2020 12","authors":["Han Shi","Renjie Pi","Hang Xu","Zhenguo Li","James T. Kwok","Tong Zhang"],"abstract":"Neural Architecture Search (NAS) has shown great potentials in finding better neural network designs. Sample-based NAS is the most reliable approach which aims at exploring the search space and evaluating the most promising architectures. However, it is computationally very costly. As a remedy, the one-shot approach has emerged as a popular technique for accelerating NAS using weight-sharing. However, due to the weight-sharing of vastly different networks, the one-shot approach is less reliable than the sample-based approach. In this work, we propose BONAS (Bayesian Optimized Neural Architecture Search), a sample-based NAS framework which is accelerated using weight-sharing to evaluate multiple related architectures simultaneously. Specifically, we apply Graph Convolutional Network predictor as a surrogate model for Bayesian Optimization to select multiple related candidate models in each iteration. We then apply weight-sharing to train multiple candidate models simultaneously. This approach not only accelerates the traditional sample-based approach significantly, but also keeps its reliability. This is because weight-sharing among related architectures are more reliable than those in the one-shot approach. Extensive experiments are conducted to verify the effectiveness of our method over many competing algorithms.","url_abs":"https://arxiv.org/abs/1911.09336v4","url_pdf":"https://arxiv.org/pdf/1911.09336v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-objective-neural-architecture-search-1","repo_url":"https://github.com/automl/NASLib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.09336","atlas_url":"https://app.syntology.ai/?focus=1911.09336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}