{"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/overcoming-multi-model-forgetting-in-one-shot","title":"Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization","arxiv_id":null,"date":"2020-06-01","proceeding":"CVPR 2020 6","authors":["Miao Zhang"," Huiqi Li"," Shirui Pan"," Xiaojun Chang"," Steven Su"],"abstract":"One-Shot Neural Architecture Search (NAS) significantly improves the computational efficiency through weight sharing. However, this approach also introduces multi-model forgetting during the supernet training (architecture search phase), where the performance of previous architectures degrade when sequentially training new architectures with partially-shared weights. To overcome such catastrophic forgetting, the state-of-the-art method assumes that the shared weights are optimal when jointly optimizing a posterior probability. However, this strict assumption is not necessarily held for One-Shot NAS in practice. In this paper, we formulate the supernet training in the One-Shot NAS as a constrained optimization problem of continual learning that the learning of current architecture should not degrade the performance of previous architectures during the supernet training. We propose a Novelty Search based Architecture Selection (NSAS) loss function and demonstrate that the posterior probability could be calculated without the strict assumption when maximizing the diversity of the selected constraints. A greedy novelty search method is devised to find the most representative subset to regularize the supernet training. We apply our proposed approach to two One-Shot NAS baselines, random sampling NAS (RandomNAS) and gradient-based sampling NAS (GDAS). Extensive experiments demonstrate that our method enhances the predictive ability of the supernet in One-Shot NAS and achieves remarkable performance on CIFAR-10, CIFAR-100, and PTB with efficiency.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Overcoming_Multi-Model_Forgetting_in_One-Shot_NAS_With_Diversity_Maximization_CVPR_2020_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhang_Overcoming_Multi-Model_Forgetting_in_One-Shot_NAS_With_Diversity_Maximization_CVPR_2020_paper.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":"overcoming-multi-model-forgetting-in-one-shot","repo_url":"https://github.com/MiaoZhang0525/NSAS_FOR_CVPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}