{"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-graph-structured-sum-product","title":"Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps","arxiv_id":"1709.08274","date":"2017-09-24","proceeding":null,"authors":["Kaiyu Zheng","Andrzej Pronobis","Rajesh P. N. Rao"],"abstract":"We introduce Graph-Structured Sum-Product Networks (GraphSPNs), a\nprobabilistic approach to structured prediction for problems where dependencies\nbetween latent variables are expressed in terms of arbitrary, dynamic graphs.\nWhile many approaches to structured prediction place strict constraints on the\ninteractions between inferred variables, many real-world problems can be only\ncharacterized using complex graph structures of varying size, often\ncontaminated with noise when obtained from real data. Here, we focus on one\nsuch problem in the domain of robotics. We demonstrate how GraphSPNs can be\nused to bolster inference about semantic, conceptual place descriptions using\nnoisy topological relations discovered by a robot exploring large-scale office\nspaces. Through experiments, we show that GraphSPNs consistently outperform the\ntraditional approach based on undirected graphical models, successfully\ndisambiguating information in global semantic maps built from uncertain, noisy\nlocal evidence. We further exploit the probabilistic nature of the model to\ninfer marginal distributions over semantic descriptions of as yet unexplored\nplaces and detect spatial environment configurations that are novel and\nincongruent with the known evidence.","url_abs":"http://arxiv.org/abs/1709.08274v2","url_pdf":"http://arxiv.org/pdf/1709.08274v2.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-graph-structured-sum-product","repo_url":"https://github.com/zkytony/graphspn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}