{"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/learning-deep-nearest-neighbor","title":"Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees","arxiv_id":"1702.08833","date":"2017-02-28","proceeding":null,"authors":["Daniel Zoran","Balaji Lakshminarayanan","Charles Blundell"],"abstract":"Nearest neighbor (kNN) methods have been gaining popularity in recent years\nin light of advances in hardware and efficiency of algorithms. There is a\nplethora of methods to choose from today, each with their own advantages and\ndisadvantages. One requirement shared between all kNN based methods is the need\nfor a good representation and distance measure between samples.\n  We introduce a new method called differentiable boundary tree which allows\nfor learning deep kNN representations. We build on the recently proposed\nboundary tree algorithm which allows for efficient nearest neighbor\nclassification, regression and retrieval. By modelling traversals in the tree\nas stochastic events, we are able to form a differentiable cost function which\nis associated with the tree's predictions. Using a deep neural network to\ntransform the data and back-propagating through the tree allows us to learn\ngood representations for kNN methods.\n  We demonstrate that our method is able to learn suitable representations\nallowing for very efficient trees with a clearly interpretable structure.","url_abs":"http://arxiv.org/abs/1702.08833v1","url_pdf":"http://arxiv.org/pdf/1702.08833v1.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":"learning-deep-nearest-neighbor","repo_url":"https://github.com/thadikari/differentiable-boundary-trees","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.08833","atlas_url":"https://app.syntology.ai/?focus=1702.08833","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}