{"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/nash-toward-end-to-end-neural-architecture","title":"NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing","arxiv_id":"1805.05361","date":"2018-05-14","proceeding":"ACL 2018 7","authors":["Dinghan Shen","Qinliang Su","Paidamoyo Chapfuwa","Wenlin Wang","Guoyin Wang","Lawrence Carin","Ricardo Henao"],"abstract":"Semantic hashing has become a powerful paradigm for fast similarity search in\nmany information retrieval systems. While fairly successful, previous\ntechniques generally require two-stage training, and the binary constraints are\nhandled ad-hoc. In this paper, we present an end-to-end Neural Architecture for\nSemantic Hashing (NASH), where the binary hashing codes are treated as\nBernoulli latent variables. A neural variational inference framework is\nproposed for training, where gradients are directly back-propagated through the\ndiscrete latent variable to optimize the hash function. We also draw\nconnections between proposed method and rate-distortion theory, which provides\na theoretical foundation for the effectiveness of the proposed framework.\nExperimental results on three public datasets demonstrate that our method\nsignificantly outperforms several state-of-the-art models on both unsupervised\nand supervised scenarios.","url_abs":"http://arxiv.org/abs/1805.05361v1","url_pdf":"http://arxiv.org/pdf/1805.05361v1.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":"nash-toward-end-to-end-neural-architecture","repo_url":"https://github.com/donggyukimc/nash","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.05361","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}