{"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/matching-convolutional-neural-networks","title":"Matching Convolutional Neural Networks without Priors about Data","arxiv_id":"1802.09802","date":"2018-02-27","proceeding":null,"authors":["Carlos Eduardo Rosar Kos Lassance","Jean-Charles Vialatte","Vincent Gripon"],"abstract":"We propose an extension of Convolutional Neural Networks (CNNs) to\ngraph-structured data, including strided convolutions and data augmentation on\ngraphs.\n  Our method matches the accuracy of state-of-the-art CNNs when applied on\nimages, without any prior about their 2D regular structure.\n  On fMRI data, we obtain a significant gain in accuracy compared with existing\ngraph-based alternatives.","url_abs":"http://arxiv.org/abs/1802.09802v1","url_pdf":"http://arxiv.org/pdf/1802.09802v1.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":"matching-convolutional-neural-networks","repo_url":"https://github.com/brain-bzh/MCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"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}