{"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/dvolver-efficient-pareto-optimal-neural","title":"DVOLVER: Efficient Pareto-Optimal Neural Network Architecture Search","arxiv_id":"1902.01654","date":"2019-02-05","proceeding":"ICLR 2019 5","authors":["Guillaume Michel","Mohammed Amine Alaoui","Alice Lebois","Amal Feriani","Mehdi Felhi"],"abstract":"Automatic search of neural network architectures is a standing research\ntopic. In addition to the fact that it presents a faster alternative to\nhand-designed architectures, it can improve their efficiency and for instance\ngenerate Convolutional Neural Networks (CNN) adapted for mobile devices. In\nthis paper, we present a multi-objective neural architecture search method to\nfind a family of CNN models with the best accuracy and computational resources\ntradeoffs, in a search space inspired by the state-of-the-art findings in\nneural search. Our work, called Dvolver, evolves a population of architectures\nand iteratively improves an approximation of the optimal Pareto front. Applying\nDvolver on the model accuracy and on the number of floating points operations\nas objective functions, we are able to find, in only 2.5 days, a set of\ncompetitive mobile models on ImageNet. Amongst these models one architecture\nhas the same Top-1 accuracy on ImageNet as NASNet-A mobile with 8% less\nfloating point operations and another one has a Top-1 accuracy of 75.28% on\nImageNet exceeding by 0.28% the best MobileNetV2 model for the same\ncomputational resources.","url_abs":"http://arxiv.org/abs/1902.01654v1","url_pdf":"http://arxiv.org/pdf/1902.01654v1.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":"dvolver-efficient-pareto-optimal-neural","repo_url":"https://github.com/guillaume-michel/dvolver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}