{"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/switchblade-a-neural-network-for-hard-2d","title":"Matrix Shuffle-Exchange Networks for Hard 2D Tasks","arxiv_id":"2006.15892","date":"2020-06-29","proceeding":null,"authors":["Emīls Ozoliņš","Kārlis Freivalds","Agris Šostaks"],"abstract":"Convolutional neural networks have become the main tools for processing two-dimensional data. They work well for images, yet convolutions have a limited receptive field that prevents its applications to more complex 2D tasks. We propose a new neural model, called Matrix Shuffle-Exchange network, that can efficiently exploit long-range dependencies in 2D data and has comparable speed to a convolutional neural network. It is derived from Neural Shuffle-Exchange network and has $\\mathcal{O}( \\log{n})$ layers and $\\mathcal{O}( n^2 \\log{n})$ total time and space complexity for processing a $n \\times n$ data matrix. We show that the Matrix Shuffle-Exchange network is well-suited for algorithmic and logical reasoning tasks on matrices and dense graphs, exceeding convolutional and graph neural network baselines. Its distinct advantage is the capability of retaining full long-range dependency modelling when generalizing to larger instances - much larger than could be processed with models equipped with a dense attention mechanism.","url_abs":"https://arxiv.org/abs/2006.15892v2","url_pdf":"https://arxiv.org/pdf/2006.15892v2.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":"switchblade-a-neural-network-for-hard-2d","repo_url":"https://github.com/LUMII-Syslab/Matrix-SE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"switchblade-a-neural-network-for-hard-2d","repo_url":"https://github.com/LUMII-Syslab/Switchblade","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"speed","method_name":"SPEED"}],"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}