{"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/attention-based-guided-structured-sparsity-of","title":"Attention-Based Guided Structured Sparsity of Deep Neural Networks","arxiv_id":"1802.09902","date":"2018-02-13","proceeding":null,"authors":["Amirsina Torfi","Rouzbeh A. Shirvani","Sobhan Soleymani","Nasser M. Nasrabadi"],"abstract":"Network pruning is aimed at imposing sparsity in a neural network\narchitecture by increasing the portion of zero-valued weights for reducing its\nsize regarding energy-efficiency consideration and increasing evaluation speed.\nIn most of the conducted research efforts, the sparsity is enforced for network\npruning without any attention to the internal network characteristics such as\nunbalanced outputs of the neurons or more specifically the distribution of the\nweights and outputs of the neurons. That may cause severe accuracy drop due to\nuncontrolled sparsity. In this work, we propose an attention mechanism that\nsimultaneously controls the sparsity intensity and supervised network pruning\nby keeping important information bottlenecks of the network to be active. On\nCIFAR-10, the proposed method outperforms the best baseline method by 6% and\nreduced the accuracy drop by 2.6x at the same level of sparsity.","url_abs":"http://arxiv.org/abs/1802.09902v4","url_pdf":"http://arxiv.org/pdf/1802.09902v4.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":"attention-based-guided-structured-sparsity-of","repo_url":"https://github.com/astorfi/attention-guided-sparsity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}